UnderstandingSociety

Power within organizations

2012-05-29T08:19:00.000-04:00

Sociologists have been thinking about organizations in a careful, empirical way for decades. Here is a volume edited by Mayer Zald that results from a 1969 conference at Vanderbilt on the topic of "Power in Organizations" (Power in Organizations). The cross-section of sociologists represented here provides a good snapshot of the ways that organizations were conceptualized in the late 1960s. There are contributions by quite a few interesting sociologists, including Peter Blau, Richard Peterson, Charles Perrow, and Mayer Zald.

Perrow's contribution, "Departmental Power and Perspectives in Industrial Firms," is particularly interesting. Here is how Perrow frames his research problem:

It is my impression that for all the discussion and research regarding power in organizations, the preoccupation with interpersonal power has led us to neglect one of the most obvious aspects of this subject: in complex organizations, tasks are divided up between a few major departments or subunits, and all of these subunits are not likely to be equally powerful. In industrial firms ... there are fairly clear divisions between the basic units of sales, production, research and development (or engineering), and finance and accounting. Equality of these groups is hardly insured by the fact that there is at least one person, the president, who stands above all these functional groups, and by the fact that each department is stratified into roughly equal levels of authority.... The question of which group dominates in industrial firms, then, will be the subject of this paper. (59-60)

Perrow's approach to the problem is empirical. His study depends on interviews with dozens of ranking employees in twelve manufacturing companies with at least 1000 employees, with 2633 individuals interviewed in total.

The study focuses on three primary groups and one "residual" group that could be identified in all the firms: sales and marketing, production and manufacturing, and research and development. The residual group is "staff services", including finance, personnel, legal, and the executive group. The research question was to determine which group or unit had the most "power" within the firm. The interview template asks a series of questions about how the interviewee estimates the power and discretion possessed by various groups within the firm.

Perrow notes that the concept of "power" conceals a range of complexities:

Do we mean actual or potential power, power derives from internal workings of the firm or the market place, power based upon the force of personalities or the logic of group functions, power today or power in the next quarter, and so on? (63)

There is a strong pattern to the results for the fundamental question, which unit has the most power? Perrow finds that "sales" is judged to have the most internal power in 10 out of 12 firms; production is generally second; "finance" is commonly third; and R&D is almost always last.

Perrow's next question is "why" -- why should sales be the most powerful unit within manufacturing firms? His answer turns on facts about the market economy. The sales operation of a company is the interface between potential consumers and the product created by the firm.

As a result of this strategic position, sales is in a position either to exploit present company capabilities or force a change in these capabilities. The consequences for the other groups are manifold, but sales -- with few sunk costs (capital investment) and little interdependence with other functions that would require major changes in its own structure and operating procedures -- is capable of more flexibility. (65)

Perrow finds this result surprising for one category of firm -- those where design and production are "non-routine", or where the product is not yet commoditized. These are what we would today refer to as high-tech firms.

If respondents described their tasks as fairly nonroutine -- indicating frequent problems requiring analysis and uncertainty about the outcomes of their efforts -- then there would be little edge for sales. (66)

So Perrow expected that R&D -- the unit assigned to develop new products and solve problems -- would have greater power in an environment of technological uncertainty. But the importance of R&D within such a firm does not cash out in terms of internal power, in Perrow's findings based on these twelve firms. And this fact, in Perrow's assessment, comes down to a tactical advantage possessed by sales within the firm:

Neither of these [prior] analyses sufficiently takes into account the ability of those who once gain power to manipulate the source of uncertainty, at least over a span of, say, ten or fifteen years. The maintenance people in Crozier's study augmented their power by removing information from the files that might make their performance more predictable and less uncertain, and by keeping information secret from machine operators and other engineers. Similarly, I think that sales, or production, or R&D can use their power to maintain either a fiction of uncertainty, or to steer the organization into areas where the uncertainty will be in their hands. (67)

So Perrow highlights an important source of power within an organization: the power to shape or hoard information.

The impression we get from reading Perrow's essay today is that Perrow's conceptual framework moves back and forth between the business environment within which a firm exists and the tactical intelligence of actors within the firm. The business environment gives an advantage to one group of actors -- those involved in sales; and the tactical actions selected by actors within that unit to maintain their advantage accounts for the persistence of the power of that unit.

What the analysis doesn't pay any attention to is the internal organization of the firm (beyond the functional division into the four units Perrow highlights). The analysis doesn't make any effort to map out the internal working relationships between functional units, or the ways in which performance of actors within units is supervised, or the ways in which communications occur internally, or the ways in which individuals are recruited into roles, or the ways in which decisions are made. The article does distinguish between levels of managers -- upper, middle, and lower -- but doesn't provide an "organizational" account of how these levels fit together. This is partly, of course, a function of the question that Perrow posed for research: what is the perceived level of power associated with the major functional units in the decision-making of the firm? But perhaps it reflects as well the development of the field. In his later writings Perrow is much more attentive to the "micro-organizations" and systemic interconnections that exist within large organizations such as FEMA or the NRC.

It is also interesting to highlight the time period in which this conference occurred: at the high-water mark of popular mobilization against the Vietnam War and segregation. The contrast between organizational power and popular protest was a stark one. And some of the organizations that are considered in the volume -- universities and medical schools, for example -- were at the center of this contrast.

Are there meso-level social causes?

2012-05-27T13:07:00.002-04:00

Social structures and other social "things" are ontologically peculiar in some ways. Most especially, they are abstract, distributed, and non-material. We can't put a culturally dominant food aversion or a group prejudice in a box and weigh it. And yet many of us want to say that social structures are "real", not merely theoretical constructs.

One important aspect of something's being real is that it has causal powers: the specific properties of the thing bring about differences in the world on the behavior of other things. This is a version of the interventionist theory of causation associated with Jim Woodward: change something about C and you bring about a change in E (link).

So let's consider this question: Can meso-level social structures have meso-level effects?

Of course meso-level structures have effects -- on individuals. The fact that there are laws and enforcement mechanisms governing highway speed has some effect on drivers' behavior. The question here is whether it is legitimate to postulate causal powers for structures whose effects are realized in other meso-level structures. And I want to explore the affirmative answer to the question: it is legitimate and coherent to assert meso-meso causal interactions, and we sometimes have empirical evidence to support such assertions.

(It would be possible, of course, to take the view that social structures are epiphenomenal and have no causal properties whatsoever. On that approach, what seems to be the effect of the legal system on individual behavior is really just the aggregate effect of the many individuals involved in the legal system. I don't find this view at all compelling, however.)

My question is relevant to two groups of sociological theorists, each of whom thinks the answer is trivial and obvious -- but in opposite directions. The new methodological individualists, represented by analytical sociology, think the answer is trivially "no", because social causation proceeds always and exclusively through actions and interactions of individuals (link). This is the fundamental idea underlying Coleman's Boat as a model of the relationship between macro and micro. And a range of anti-individualists -- Giddens, Elder-Vass, Archer -- believe it is self evident from everyday experience that causal structures do have causal powers, and that it is a waste of time to defend the notion (link). It is obvious.

My position is a precarious one. On the one hand I advocate an actor-centered approach to sociology and the social sciences. I defend the idea that social claims need microfoundations in a specific (weak) sense. And on the other hand I believe that structures have a degree of stability that permits us to couch causal claims in terms of those structures directly, rather than needing to supplement those claims with disaggregated foundations at the level of the individual. So I argue for the idea that we can sometimes regard causal powers of social entities as "relatively autonomous" from individual-level facts.

By meso-level structures I mean to refer to things like these:

National Science Foundation
Nuclear Regulatory Commission
IBM corporation
AFL-CIO
German paramilitary organizations 1930
German ideology of cultural despair 1910
Islamic norms of Zakat
...

In each case there are numerous actors assigned to roles, governed by rules defining their activities, and leading to a certain kind of functioning in the broader social environment.

Generically I would define a meso-level structure as --

A composite of individuals and roles that incorporates a set of rules and norms for internal and external actors, and that possesses procedures of inculcation and enforcement through which internal and external actors are brought to comply with the rules and norms (to some degree).

I would define a normative system as ...

a set of rules, norms, and expectations embodied in a population of actors and meeting a threshold level of success in coordinating and constraining behavior.

We have a number of sociological concepts that capture social items at this level: organization, bureaucracy, institution, normative community, social network, communications system, legal system, civil war, military coup, advocacy group.

It is evident that social entities often incorporate elements of several of these kinds of things. Organizations and structures often incorporate or depend upon normative systems, and normative systems often generate organizations and institutions that convey their impact to the young and adult actors.
What about other mid-level social nouns -- ethnic group, electorate, financial crisis, ...? These strike me as being compounds of a miscellaneous set of social things -- there are bits of organizations, normative systems, affinity groups, and social networks in each of them. The concept of assemblage seems to fit these nouns well.

The "meso" qualifier is a bit more difficult to specify. It is intended to focus our attention on mid-level social arrangements, between actors and global institutions like the US state, global Islam, and the world trading system. The intuitive idea is straightforward. These are the smaller-scale, lower-level social arrangements or units of which macro structures are composed. Bert Leuridan makes an effort to offer a more specific definition based on causal roles.

So I have a simple but important question in mind here. Is it ever legitimate to assert something like this:

Meso structure X produced changes in meso structure Y,

without being obliged to demonstrate the individual-level pathways through which this effect is thought to have come about? Is a type 4 causal claim ever supportable (link)?

The question I am posing is related to the idea of the methodological individualism associated with James Coleman. Basically the idea propounded by Coleman and more recently by the analytical sociologists is that all social properties, including causal powers, work through the activities of individuals, and we need ideally to replace claims that appear to attribute causal powers to structures with theories that disaggregate these powers onto the patterned activities of individuals. This is a reductionist theory.

Other theorists, notably Dave Elder-Vass, want to assert that social structures have "emergent" properties and powers (link). An emergent property according to E-V, is one that is possessed by the aggregate but not by the composing units. On this account, there are causal properties of structures that cannot be represented as the aggregate effect of individual actors.

My own approach depends on a line of reasoning long familiar in the special sciences. It is anti-reductionist, in that it denies that we need to derive higher-level properties from lower-level properties. It accepts the compositional ontology: social structures are composed of individual actors. But it asserts explanatory autonomy for theoretical statements about mid-level mechanisms (link, link, link).

One particularly direct way of supporting the idea that structures have meso effects is to establish correlations at that level for a few examples. But this isn't the only way we establish causation in other areas of the sciences. We do experiments ("remove X and observe whether Y persists"), we analyze the outcomes of "natural" experiments, we do comparative studies, and we engage in process tracing of particular cases. We even engage in theoretical analysis to try to determine what causal powers a certain entity ought to be expected to have given its constitution.

So it seems that there is ample room for sociologists to assert and investigate the causal properties of social structures. And given appropriate attention to the principle of microfoundations, we have a social ontology that supports the legitimacy of such claims as well.

A related question is whether there are "mechanisms" that operate at the meso level, or whether all social mechanisms must operate at the individual level (as Hedstrom and the AS world believe). I will return to this question.

The social world as morphogenesis

2012-05-23T23:20:00.002-04:00

Critical realism has progressed far since Roy Bhaskar's early writings on the subject in A Realist Theory of Science. One of the most important thinkers to have introduced new ideas into the debate is Margaret Archer. Several books in the mid-1990s represented genuinely original contributions to issues about the nature of social ontology and methodology, including especially Realist Social Theory: The Morphogenetic Approach and Culture and Agency: The Place of Culture in Social Theory.

Archer's work addresses several topics of interest to me, including especially the agent-structure dichotomy. This is key to the twin concerns I have for "actor-centered social science" and "autonomous meso-level explanations". Anthony Giddens offers one way of thinking about the relationship between agents and structures (link). Archer takes issue with the most fundamental aspect of Giddens's view -- his argument that agents and structures are conceptually inseparable. Archer argues instead for a form of "dualism" about agents and structures -- that each pole needs to be treated separately and in its own terms. (Chapter 5 provides a detailed discussion of both Bhaskar and Giddens on levels of the social.) She acknowledges, of course, that social structures depend on the individuals who make them up; but she doesn't believe that this basic fact tells us anything about how to analyze or explain facts about either agents or structures. Here are the opening paragraphs of Realist Social Theory.

Social reality is unlike any other because of its human constitution. It is different from natural reality whose defining feature is self-subsistence: for its existence does not depend upon us, a fact which is not compromised by our human ability to intervene in the world of nature and change it. Society is more different still from transcendental reality, where divinity is both self-subsistent and unalterable at our behest; qualities which are not contravened by responsiveness to human intercession. The nascent 'social sciences' had to confront this entity, society, and deal conceptually with its three unique characteristics.

Firstly, that it is inseparable from its human components because the very existence of society depends in some way upon our activities. Secondly, that society is characteristically transformable; it has not immutable form or even preferred state. It is like nothing but itself, and what precisely it is like at any time depends upon human doings and their consequences. Thirdly, however, neither are we immutable as social agents, for what we are and what we do as social beings are also affected by the society in which we live and by our very efforts to transform it. (1)

Archer argues that the two primary approaches that theorists have taken -- methodological individualism and methodological holism -- are fundamentally inadequate. They represent what she calls upward and downward conflation. In the first case, "society" disappears and is replaced by some notion of aggregated individual action; in the second case "agents" disappear and the human individuals do no more than act out the imperatives of social norms and structures. She associates the first view with J.S. Mill and Max Weber and the second view with Durkheim. On her view, agents and structures are distinct, and neither is primary over the other.

She refers to her view as the "morphogenetic" approach. Here is how she explains this concept:

The 'morpho' element is an acknowledgement that society has no pre-set form or preferred state: the 'genetic' part is a recognition that it takes its shape from, and is formed by, agents, originating from the intended and unintended consequences of their activities. (5)

Morphogenesis applies at all levels, from "the capitalist system" to "the firm" to "the actor" to personal identity and motivation. And she believes that properties at various levels -- micro and macro -- have a degree of autonomy from each other, which she refers to as "emergence":

I want to maintain that 'micro' and 'macro' are relational terms meaning that a given stratum can be 'micro' to another and 'macro' to a third etc. What justifies the differentiation of strata and thus use of the terms 'micro' and 'macro' to characterize their relationship is the existence of emergent properties pertaining to the latter but not to the former, even if they were elaborated from it. (9)

Later in the book she amplifies this idea:

Autonomy is also temporal (and temporary) in the joint senses that such structural properties were neither the creation of contemporary actors nor are ontologically reducible to 'material existents' (raw resources) and dependent upon current acts of human instantiation (rule governed) for all their current effects. (138)

And this is where her theory exhibits its "realism": she asserts that the properties we identify at various levels or "strata" are real and causally powerful.

Thus in the course of this book, frequent references will be made to 'the societal'. Each time, this has a concrete referent - particular emergent properties belonging to a specific society at a given time. Both the referent and the properties are real, they have full ontological status, but what do they have to do with 'the big'? The society in question may be small, tribal and work on a face-to-face basis. Nor do they have anything to do with what is, relatively, 'the biggest' at some point in time. We may well wish to refer to certain societal properties of Britain (the 'macro' unit for a particular investigation) which is an acknowledged part of bigger entities, like Europe, developed societies, or the English speaking world. We would do so if we wanted to explain, for example, the role of the 'Falklands factor' in recent elections and in so doing we would also incidentally be acknowledging that people who go in for it take their nationalism far from 'impersonally', and that the 'site' of neo-colonialism may be far distant. (10)

And she offers a different way of thinking about "micro" and "macro" -- not from small to large, but from interactional and local to systemic (11).

This all adds up to a social realism that is militant in affirming the reality of social properties as emergent properties.

Conversely social realism which accentuates the importance of emergent properties at the level of both agency and structure, but considers these as proper to the strata in question and therefore distinct from each other and irreducible to one another, replaces the terms of the traditional debate with entirely new ones. Irreducibility means that the different strata are separable by definition precisely because of the properties and powers which only belong to each of them and whose emergence from one another justifies their differentiation as strata at all. (14)

So what is Archer's central notion, the idea of morphogenesis? It is the idea that processes of change occur for agents and social structures in interlocking and temporally complex ways. Agents are formed within a set of social structures -- norms, language communities, power relationships. The genesis of the agent occurs within the context of these structures. On a larger time scale, the structures themselves change as a result of the activities and choices of the historically situated individuals who make them up. She summarizes this ontology as a set of cycles with different time frames: structural conditioning => social interaction => structural elaboration (16). This notion leads Archer to a conception of the social and the actor that reflects a fundamentally historical understanding of social processes. Formation and transformation are the central metaphors (154).

A final comment about Archer's philosophy of social science is relevant here. She provides a theory which is abstract and philosophical -- ontology, debates about emergence and reduction, epistemology. But she does so in consideration of her own detailed research on the history and development of an important aspect of social reality, educational institutions. So her abstract philosophical ideas are grounded not only in philosophy but also in historical and sociological research.

Perhaps I'm over-interpreting, but it seems to me that Archer's realist theory of morphogenesis is highly complementary to the ideas about methodological localism that have been argued for here. The idea that actors are socially constituted and socially situated (methodological localism) is a different way of expressing her point that actors are constituted by surrounding social structures. The idea that structures are themselves adapted and changed by active individuals doing things within them corresponds to her "social interaction" and "structural elaboration" phases of morphogenesis. The methodological insight that seems to come along with morphogenesis -- the idea that it is valuable to move both upwards towards more comprehensive social structures and downwards towards more refined understanding of action and interaction -- is certainly a part of the view associated with methodological localism and actor-centered sociology. Her view of the inherent "transformability" of society (1) parallels my own view of the heterogeneity and contingency of social arrangements. Finally, her notion that social ontology must be addressed before we can make much progress on issues of methodology and explanation seems right to me as well.

Giddens on agents and structures

2012-05-21T20:46:00.001-04:00

Anthony Giddens is one of the theorists whose ideas are most often invoked when the idea of social-structural explanation is in play. His 1979 collection of essays, Central Problems in Social Theory: Action, Structure, and Contradiction in Social Analysis, is a classic statement of some of his views. Here is how he frames his core concern in a key essay, "Agency, Structure":

The principal issue with which I shall be concerned in this paper is that of connecting a notion of human action with structural explanation in social analysis. The making of such a connection, I shall argue, demands the following: a theory of the human agent, or of the subject; an account of the conditions and consequences of action; and an interpretation of 'structure' as somehow embroiled in both those conditions and consequences. (49)

Giddens refers some of these issues back to the tradition of American pragmatism, and the theories of George Herber Mead in particular (link).

Within more orthodox sociological traditions, symbolic interactionism has placed most emphasis upon regarding social life as an active accomplishment of purposive, knowledgeable actors; and it has also been associated with a definite 'theory of the subject', as formulated in Mead's account of the social origins of reflexive consciousness. (50)

Giddens faults this tradition for not being able to conceptualize the social-structural context with sufficient precision. He finds, for example, that Durkheim's efforts to provide theoretical resources for describing the "external or objective" character of society were inadequate (51). Generally his view here is that theorists have failed in their conceptualizations of structures and agents:

Parson's actors are cultural dopes, but Althusser's agents are structural dopes of even more stunning mediocrity. (52)

The problem is that neither individualists nor structuralists have succeeded in expressing the inherent interdependence of the two poles. Give primacy to structures and the agents are "dopes" -- robots controlled by structural conditions. Give primacy to individuals, and structures and institutions seem to disappear. His own view is that the two poles of structure and agency must be considered from within a common formulation:

I shall argue here that, in social theory, the notions of action and structure presuppose one another; but that recognition of this dependence, which is a dialectical relation, necessitates a reworking both of a series of concepts linked to each of these terms, and of the terms themselves. (53)

Giddens observes that action necessarily implies a temporal framework.

'Action' or agency, as I use it, thus does not refer to a series of discrete acts combined together, but to a continuous flow of conduct. We may define action ... as involving a 'stream of actual or contemplated causal interventions of corporeal beings in the ongoing process of events-in-the-world'. (55)

Actions take place in contexts; and the contexts include crucially the actions of other people and the constraints and opportunities created by social structures. Giddens adds another component of action: the forms of knowledge that actors have on the basis of which they tailor their interventions.

So what about "structure"? Giddens prefers to talk about "structuration" -- the temporally extended processes through which social constraints evolve and take hold.

I want to suggest that structure, system and structuration, appropriately conceptualised, are all necessary terms in social theory. (62)

What is a "structure"? Here is one effort at definition provided by Giddens:

The term 'social structure' thus tends to include two elements, not clearly distinguished from one another: the patterning of interaction, as implying relations between actors or groups; and the continuity of interaction in time. (62)

He refers to these two aspects as "syntagmatic" and "paradigmatic" dimensions of social structures. And he summarizes the concept of structure in these terms: "the rules (and resources) that, in social reproduction, 'bind' time" (63). "Structures can be identified as sets or matrices of rule-resource properties" (63-64). Here is a summary table:

source: Giddens, Central Problems in Social Theory, p. 66.

The activity of structuration is key to Giddens's theorizing agents and structures, because it represents the link between the two.

The concept of structuration involves that of the duality of structure, which relates to the fundamentally recursive character of social life, and expresses the mutual dependence of structure and agency. (69)

Knowledge plays a key role in structuration; it provides the basis on which agents both understand and transform the rules around them. Agents, in other words, are reflexive cognitive actors.

Institutions involve signification, domination and legitimation (106). In "Institutions, Reproduction, Socialisation" Giddens talks about structures in terms of means of mediation and transformation within a collection of active participants.

I want to suggest that each of the three aspects of structure I have distinguished can be understood as ordered in terms of the mediations and transformations which they make possible in the temporal-spatial constitution of social systems.... Writing and other media of communication ... bind much greater distances in time and space. (103)

A distinction that comes up a lot in Giddens's work in this collection is that between synchronic and diachronic states of affairs. We can think of a structure as a snapshot at a moment in time of a set of relations, beliefs, rules, and opportunities. This would be a synchronic description of the structure; it is a static approach to a social structure. Or we can look at a structure as being in a process of generation, reproduction, and transformation; this would be a diachronic and dynamic way of thinking about structures. Giddens's affinity to the idea of structuration suggests that he is especially interested in the dynamic questions -- the ways in which actors, roles, and rules interact over time, leading to changes in the snapshot.

What Giddens's treatment here doesn't adequately express, in my reading, is what we think structures and institutions really are. Are they complexes of patterned activities by numbers of actors? Are they ensembles of social practices? Is the IBM corporation simply a large set of social interactions? Or is there an abiding abstract social reality -- division of labor and authority; segmentation of responsibilities; interlocking productive activities -- that can be identified as a social entity? What about the capitalist economic structure; is this a stable social entity, or is it simply an ensemble of patterns of relations of meaning and power? It seems that these examples are the kinds of thing that Giddens wants to refer to as a "system"; but it's not clear.

So the concept of social structure still seems underdeveloped here. What about the idea that agent and structure are inseparable? This I understand in a fairly direct way: agents are always located in a web of social relationships that define them and define the opportunities they confront. And structures are always constituted by individuals thinking, acting, and interacting in specific ways. So we literally cannot separate agents and structures; they are mutually constitutive.

(Here is an intriguing dynamic network simulation of the spread of HIV infection based on data from the National Longitudinal Study of Adolescent Health. "Small differences in reported behavior can potentially explain the large racial disparities in HIV infection observed in the United States.")

Does "culture" require microfoundations?

2012-05-19T16:55:00.000-04:00

I have consistently argued for a philosophy of social science that emphasizes the actor and the availability of microfoundations. I argue for an actor-centered sociology. But I have lately been arguing as well for the idea that it is legitimate for social scientists to treat claims about the causal properties of meso-level social structures as being relatively autonomous from their microfoundations.

This approach doesn't satisfy all comers. Some don't like meso-level causal properties at all, and others don't like the idea that meso-level properties are in any way dependent on the level of individuals and their actions and agency.

In particular, some readers would prefer a meso-autonomist strategy that dispenses with individuals altogether; one according to which we can identify certain causal factors that do not need microfoundations at the level of the individual at all. Candidates for such factors often fall under the large umbrella of culture: symbols, meanings, practices, rituals, traditions, grammars, and the like. I would say, however, that these items too require microfoundations. Cultural items are sometimes thought to be supra-individual and independent from the concrete individuals who live within their scope. And it is true that culture exercises a specific kind of independence. But no less than any other social characteristic can cultural features evade their embodiment in individual actors and institutions.

If we take the view that the obligations of zakat (charity) are a profound part of Muslim identity and that this element of Islam explains certain social outcomes, then I want to know how these elements of identity are conveyed to children and practitioners at the local level. What are the concrete social mechanisms of inculcation and communication through which a Bangladeshi child comes to internalize a full Muslim identity, including adherence to the norms of zakat? To what extent are there important differences within Bangladeshi society in the forms of identity present in Muslims -- urban-rural, male-female, rich-poor? And equally interestingly – in what ways do those processes give rise to a Muslim identity in Bangladesh that is somewhat different from that in Indonesia, Morocco, or Saudi Arabia?

Identities, cultures, and systems of meaning are no less embodied in the states of mind of actors than are the calculating features of rationality that underlie a market society. So the fault of methodological individualists in this sphere is not that they fail to recognize the inherent autonomy of systems of cultural meaning; it is rather that they adhere to a theory of the actor that does not give sufficient attention to the variations and contingencies that characterize actors in various social and historical contexts. Ideas about the independence of cultural items from the level of individuals are suggestive and interesting, and I think they need to be fully confronted by an actor-centered sociology. But I do not believe they are incompatible with an actor-centered sociology.

Take the independence of a code of behavior from the specific individuals who are subject to the code. It is true that one individual cannot influence the code, which is embodied in the thoughts and actions of countless others. But the reality of the code at any given time is in fact entirely dependent on those thoughts and actions (and artifacts created by previous actors). Moreover, the individual's embodiment of the code of behavior is in turn caused by a series of interactions through childhood and adulthood within a social setting.

It is certainly true that facts about culture make a difference in meso- and macro-level outcomes. A collective farm that was populated by actors who embodied Chairman Mao’s ideal of “socialist man” would have functioning characteristics very different from those observed -- no “easy riders,” lots of earnest Stakhanovites. So standard organizational analysis of the tendencies towards low productivity in collective agriculture is dependent on something like a purposive agent theory of the actor. Different kinds of actors give rise to different kinds of organizations.

This does not mean, however, that we could not have reasonably good understandings of “organizations” under differently realized structures of agency. This seems to be part of the work that Andreas Glaeser (2011) is doing in Political Epistemics: The Secret Police, the Opposition, and the End of East German Socialism. Glaeser tries to understand how organizations like the Stasi functioned in a setting in which participants’ understandings and motivations were changing rapidly.

So my answer to my own question is, yes. Cultural entities and characteristics do require microfoundations, and it is in fact a fruitful avenue of sociological and ethnographic investigation to discover the concrete social mechanisms and pathways through which these entities come to be embodied in various populations in the ways that they are.

Scaling up

2012-05-16T22:15:00.000-04:00

City Year is a pretty unusual and impressive social-entrepreneurial organization (link). Founded in 1988 as a platform for providing young Americans an opportunity to provide a year of service in an urban environment, the organization has grown dramatically in the intervening 24 years. Here is the organization's mission statement:

City Year’s mission is to build democracy through citizen service, civic leadership and social entrepreneurship. It is through service that we can demonstrate the power and idealism of young people, engage citizens to benefit the common good, and develop young leaders of the next generation.

In the coming year something like 2,500 corps members will contribute a year of service in some 24 cities in the United States and another four cities internationally. Secretary of Education Arne Duncan offered a keynote address to this month's City Year leadership summit in Washington that made it clear how important City Year's goals are for the nation as a whole. Duncan describes this as the civil rights issue of our generation.

One thing that I find interesting about the evolution of City Year over the past ten years is the refinement of focus its leadership has effected with regard to the way in which the talents and energy of corps members are deployed. Michael Brown has proven to be a highly effective leader (as well as co-founder), and he has drawn a strong group of senior leaders around him. In the early years the focus was on the value of youth service, allowing young people to contribute to the improvement of their communities in a variety of ways. For the past eight years or so the organization has come to the realization that service by itself is not enough. The service activities of the willing need to be coordinated around projects that can have real, sustainable impact. We need an effective and attainable strategic plan of action for service.

Involvement in schools has always been part of the palette of youth service at City Year. But in the past six years or so the focus has sharpened to allow City Year organizations in various cities to make a measurable impact on a very serious problem, the high school dropout rate in many American cities. In many cities fewer than half of a given cohort actually graduate on time. This failure rate has serious costs, both for the individuals and their families, and for the communities in which they live. And this problem is strongly stratified by poverty and race.

City Year's central leadership in Boston therefore partnered with Bob Balfanz, an education scholar at Johns Hopkins (link), in order to focus on a diagnosis of how high school completion could be increased for inner city young people. Here is how Balfanz puts the problem this way in a recent white paper (link):

As a result, in order to achieve the educational outcomes the nation needs, it must solve the poverty challenge. To do this, we need a deep understanding of how poverty impacts educational outcomes. Strong arguments can be made that the very reforms currently being championed at the federal and state level—a common core curriculum linked to college and career ready standards, improved teacher quality, and turning around the lowest performing schools—are essential to solving the poverty challenge.

The theory is a simple one. Balfanz argues, based on extensive educational data, that there are three indicators that are very strong predictors of a child's eventually becoming a high school dropout, as early as the sixth grade. These indicators are attendance, behavior, and course success. Sixth graders who are deficient in any one of these indicators have a dramatically lessened likelihood of graduation from high school. Here is Balfanz again:

In order to overcome the poverty challenge, schools that serve high concentrations of low income students need to be able to provide direct, evidence-based supports that help students attend school regularly, act in a productive manner, believe they will succeed, overcome external obstacles, complete their coursework, and put forth the effort required to graduate college-and-career ready.

So now the agenda for City Year has now been focused more sharply. Teams of City Year corps members are placed in schools, including middle schools and high schools, and their time and effort are focused on bringing at-risk students up to par in each of these areas. They provide near-peer counseling, tutoring, behavior adjustment, and attendance support, and they often create very strong relationships with the students they help. A particularly focused program is in place in a select number of schools, called the Diplomas Now program. This is a cooperative relationship between City Year, Communities in Schools, and the Johns Hopkins educational researchers. And the assessment data for the schools is very encouraging. Dramatic improvements in the three areas of focus are measured across the country.

The aspiration of the City Year national organization has been to reach 50% of the at-risk students throughout urban America.

City Year’s In School and On Track initiative is designed to bring City Year corps members to 50% of all of the students falling off track in City Year’s 23 U.S. locations, which will require expanding the number of corps members to 6,000 and engaging school districts, the private sector and the federal government through AmeriCorps as partners.

This is a big goal. What is impressive is the fact that City Year is making real progress towards attaining this goal. (Here is a press release documenting recent progress.) And this is in turn a very powerful example of how a social justice organization can actually make serious progress on a pervasive social problem. It can contribute to a "Race to the Moon" effort to ensure a high school equation for all of America's young people, and a decent foundation for a college education as well.

Here is a great animated video that City Year has produced to explain its current goals in addressing the dropout crisis.

Slow institutional change

2012-05-14T16:10:00.001-04:00

Institutions are interlocking sets of rules and practices that shape specific sets of actors to behave this way rather than that. The institutions governing public comment on newly proposed regulations provide an interesting case in point. Citizens have interests with respect to new policies, and the rules and formal processes define the means through which they are permitted to express their concerns formally as part of the process. The specific ways through which comments are solicited and processed make a difference for the quality and effectiveness of citizen feedback on public regulatory regimes.

There are several interesting questions that arise concerning institutions. First, how do they come about in the first place? Second, what processes and forces maintain institutions over time, so that they have a degree of stability? And third, what factors cause change in institutions,either gradually or dramatically?

Jack Knight and various collaborators have a basis for one kind of answer to both the second and the third questions. Their framework emphasizes the role that powerful actors exert in both sustaining and changing institutions. (Mahoney and Thelen note that historical institutionalists commonly take a perspective along these lines; kl 294). Rather than imagining that institutions somehow evolve so as to optimize the public good, they argue that we can understand many instances of institutional change as adaptations stimulated by the efforts of powerful actors influenced by the institution. (Charles Perrow's account of the evolution of land use near the Mississippi River is a case in point. Developers rather than farsighted legislators set the terms of the policies (The Next Catastrophe: Reducing Our Vulnerabilities to Natural, Industrial, and Terrorist Disasters (New in Paper); kl 5198.)

The causal issues boil down to two main directions of social causation: first, from a set of individual and social circumstances to the structure and functioning of a given institution. (For example, how did competition between landed interests and business interests influence the evolution of the House of Lords in the nineteenth century?) And second, from the specifics of the institution to patterns of individual behavior and to patterns of persistence and change in social arrangements exterior to the institution. (For example, how did the constitution and rules of functioning of the House of Lords influence the pace of social welfare policies in Great Britain?)

A very interesting recent contribution to this set of issues is a volume edited by James Mahoney and Kathleen Thelen, Explaining Institutional Change: Ambiguity, Agency, and Power. The collection offers a new framework for analyzing institutional change and includes stellar contributions by Tulia Falleti, Ato Kwamena Oomo, Alan Jacobs, Dan Slater, Adam Sheingate, and Peter Hall. The issues involved here are highly relevant to the ongoing thread of interest here concerning "meso" level causation. Mahoney and Thelen review the three main tributaries of institutionalism theory -- institutionalist sociology, rational choice institutionalism, and historical institutionalism -- and they argue that each approach leaves an important gap: what factors internal to institutions are relevant to their patterns of stability and change over time? This collection represents a group of researchers interested in exactly that family of questions.

Here are a few defining questions that guide the research summarized in the volume.

Exactly what properties of institutions permit change? How and why do the change-permitting properties of institutions allow (or drive) actors to carry out behaviors that foster the changes (and what are those behaviors)? How should we conceptualize these actors? What types of strategies flourish in which kinds of institutional environments? What features of the institutions themselves make them more or less vulnerable to particular kinds of strategies for change? (kl 208)

A particularly important part of the new framework is the idea that capacity for change is embedded within institutions. So the idea that institutional change results from exogenous shock is rejected.

We propose that the basic properties of institutions contain within them possibilities for change. What animates change is the power-distributional implications of institutions. (kl 414)

One key internal feature that this approach identifies as promoting change is ambiguity:

Compliance is inherently complicated by the fact that rules can never be precise enough to cover the complexities of all possible real-life situations. When new developments confound the rules, existing institutions may be changed to accommodate the new reality. These changes can involve rule creation, or they may simply entail creative extensions of existing rules to the new realities. (kl 379)

So what happens when institutions change? Mahoney and Thelen categorize gradual change into four types: displacement, layering, drift, and conversion (kl 444). And they argue that these categories are significant given the different roles that actors and strategies play in each of them. (This categorization seems to have something in common with the way geneticists and ecologists might characterize different modalities of adaptation within a changing environment.) They provide a 2x2 table that predicts the kind of adaptation that will occur, depending on combinations of strong/weak veto possibilities and low/high levels of discretion in interpretation of rules. For example, they assert that strong veto associated with high discretion produces drift rather than layering or conversion. They offer a similar analysis of different types of change agents, and attribute different kinds of strategies to the different categories of change agents.

How does this framework relate to the topics of "actor-centered" social science and "meso-level causation" that have been considered in earlier posts? The theoretical framework Mahoney and Thelen describe is clearly actor-centered. They are focused on identifying the ways in which different categories of actors are empowered to interact with various features of a set of institutional rules. This picture seems to correspond to the ascending and descending links of the macro-micro analysis proposed by Coleman's boat.

Institutions are just the sorts of social entities that I want to say are meso structures with causal properties. That said, the analysis provided by Mahoney and Thelen offers few examples of meso-meso causation. This isn't to say that their approach doesn't countenance such relations, but only that this isn't the focus of analysis in the current set of studies.

European philosophy of social science

2012-05-09T21:47:00.000-04:00

There is an active and extended group of scholars in Europe with a very focused concentration on the philosophy of the social sciences. A good cross-section of this community gathered in Rotterdam Monday and Tuesday this week for a small conference on social mechanisms at the Erasmus Institute for Philosophy and Economics (link). These are for the main part younger scholars up to 15 years out from the PhD. And they are a genuinely impressive group of researchers.

There is a common set of topics and references that bind this extended research community together from Finland to Belgium to the Netherlands to Italy. They share a focus on social explanation. They are intellectually committed to the construct of "causal mechanisms" rather than causal laws. They have affinities and connections to the Analytical Sociology network, though few would explicitly identify themselves as analytical sociologists. Jim Woodward's theory of causation, the classic paper by Machamer, Darden, and Craver ("Thinking about Mechanisms", 2000), and Carl Craver's theorizing about mechanisms and levels in the neurosciences represent a few common intellectual landmarks, and almost all of these young scholars are current with the latest twists and turns of Peter Hedstrom's theories.

Finally, there is a decided absence of classic European voices about the social sciences -- conversations never invoke Bourdieu, Habermas, or Gadamer. This is a community organized around the intellectual values of analytic philosophy -- clarity, logical rigor, analysis, and causality.

There is also a high degree of interaction among members of this group. Mini conferences and workshops are able to bring many of them together, with the European rail system making it feasible to travel from London, Amsterdam, and Paris for a short conference in Ghent. In my observation this easy interaction stimulates a great deal of intellectual progress year after year, both individually and collectively.

As one small example, Bert Leuridan's effort this week to specify a rigorous relationship between meso and macro levels of a social system will certainly be fruitful for a number of us as we think further about this issue. And likewise, I will be interested to reflect further on Petri Ylikoski's call for a "flat" understanding of social causes. These examples illustrate the micro-steps of the advancement of a body of thought.

Sometimes it is difficult to see whether an intellectual field is progressing or just retracing old ground. Lakatos's ideas of "progressive" and "degenerative" research communities seem useful here. European philosophy of social science seems to be making real progress in this generation.

There is one academic reality that is worrisome. Many of these young scholars are making their way on the basis of research appointments and post-doc positions. These opportunities are pretty well funded by European universities and governments -- substantially more so than in the US. But many of these positions have a maximum term of six years. And the prospects of a regular faculty position in Europe seem bleak. A department chair estimated to me that only 20% of PhDs eventually find regular academic positions. This suggests an academic ecology that may prove stifling for the kinds of innovation we now see.

I think there could be a useful piece of research within the new sociology of ideas advocated by Neil Gross and and Charles Camic (link) based on this example. It wouldn't be difficult to draw out a network map of relationships among these philosophers, the major institutions that facilitate their work, and the movement of various new ideas through their conference papers and published work. Looking backward, it would be feasible as well to reconstruct the generation of writers and scholars who helped shape this generation's intellectual agenda. And I think the results would be very interesting.

It would also be interesting to begin developing a shared map of centers and locations of work on the philosophy of social science in Europe. Here is a start -- it's set for public access, so please feel free to add other points of interest, including centers, conferences, and concentrations of researchers.

View European Philosophy of Social Science in a larger map

Does the microfoundations principle imply reductionism?

2012-05-06T05:59:00.001-04:00

My philosophy of social science has always and consistently maintained the idea that social facts depend on the activities and beliefs of individuals. There is no social "stuff" that exists independently from individual actors. I have encapsulated that idea in the form of the "microfoundations" principle: any claim about the characteristics or causal powers of social entities must be compatible with there being microfoundations for those properties and powers at the level of the actor.

At the same time, I also believe that there is an appropriate domain for social science: the exploration of the features and powers of the social world. I don't believe that methodology should force the sociologist to become a psychologist or to shift his/her attention to the micro level.

Are these two premises compatible? Or does the microfoundations principle actually entail reductionism? Does it imply that explanations couched at the level of social vocabulary are incomplete and derivative, and that the real explanation must be found at the level of the micro-activities of individuals?

I attempt to resolve this apparent dilemma by distinguishing between strong and weak versions of the microfoundations principle: "social explanations must provide microfoundations for their assertions about social properties and powers" versus "social explanations must be compatible with there being microfoundations for their assertions about social powers and properties." The weak version reflects an appropriate stipulation based on what we know about the ontology of the social world, whereas the strong version is a kind of explanatory reductionism that is unjustified.

My position, then, is that sociology is a special science in Fodor's sense, and that sociologists both can and do treat their domain as relatively autonomous.

Several commentators allege that my commitment to microfoundations -- which is unwavering -- vitiates my ability to claim relative explanatory autonomy for the meso level. Some don't like my distinction between weak and strong microfoundations, and others think that commitment to MF means explanations have to proceed through explicit discoveries of the MF pathways.

My position is intended to exactly parallel physicalism in cognitive science: we are committed to the idea that all cognitive processes are somehow or other embodied and carried out by the central nervous system. But we are not obliged to actually perform that reduction in offering a hypothesis and explanation at the level of cognitive systems.

Even more prosaically: we believe that the properties of metals depend upon the quantum properties of subatomic particles. Does anyone seriously believe that civil engineers aren't giving real explanations of bridge failures when they refer to properties like tensile strength, compression indices, and mechanisms like metal fatigue? We can observe and measure the metal's properties without being forced to provide a quantum mechanical deduction.

One observer writes that "Little's examples actually confirm that meso-level mechanisms work only through micro-level processes." Yes, and I likewise confirm that cognitive processes work only through neural events and material properties work only through quantum physics. But I don't accept that this demonstrates that the higher level cannot be treated as having real causal properties. It does have those properties; and we simply reaffirm the point that somehow or other those properties are embodied in the lower level elements. This isn't a new idea; it was contained in Jerry Fodor's "Special Sciences" article years ago. If the argument is generally a bad one then we are forced to undo a lot of work in cognitive science. If it is generally compelling but inapplicable to social entities then we need to know why that is so in this special case of a special science.

To be clear, I too believe that there is a burden of proof that must be met in asserting a causal power or disposition for a social entity -- something like "the entity demonstrates an empirical regularity in behaving in such and such a way" or "we have good theoretical reasons for believing that X social arrangements will have Y effects." And some macro concepts are likely cast at too high a level to admit of such regularities. That is why I favor "meso" social entities as the bearers of social powers. As new institutionalists demonstrate all the time, one property regime elicits very different collective behavior from its highly similar cousin. And this gives the relevant causal stability criterion. Good examples include Robert Ellickson's new-institutionalist treatment of Shasta County and liability norms and Charles Perrow's treatment of the operating characteristics of technology organizations. In each case the microfoundations are easy to provide. What is more challenging is to show how these social causal properties interact in cases to create outcomes we want to explain.

The best reason I am aware of to doubt stable causal powers for social entities is founded on the point that organizations and institutions are too plastic to possess enduring causal properties over time. I've made this argument myself on occasion. But researchers like Kathleen Thelen in The Evolution of Institutions demonstrate that there are in fact some institutional complexes that do possess the requisite stability.

So I continue to believe both things: that statements about social entities and powers must be compatible there being microfoundations for these properties and powers; and that it is theoretically possible that some social structures have properties and powers that are relatively autonomous, in the sense that we can allude to those properties and powers in explanations without being obliged to demonstrate their microfoundations.

Macro causes of European fascism

2012-05-03T16:04:00.000-04:00

Michael Mann's book Fascists makes use of causal claims at a range of levels, from the macro to the micro, to explain the emergence of European fascism. Here is a passage that highlights four macro-level causes of fascism:

The interwar period in Europe was the setting that threw up most of the self-avowed fascists and saw them at their high tide. My definition is intended firstly as “European-epochal,” to use Eatwell’s (2001) term (cf. Kallis 2000: 96), applying primarily to that period and place – though perhaps with some resonance elsewhere. The period and the continent contained four major crises: the consequences of a devastating “world,” but in fact largely European, war between mass citizen armies, severe class conflict exacerbated by the Great Depression, a political crisis arising from an attempted rapid transition by many countries toward a democratic nation-state, and a cultural sense of civilizational contradiction and decay. Fascism itself recognized the importance of all four sources of social power by explicitly claiming to offer solutions to all four crises. And all four played a more specific role in weakening the capacity of elites to continue ruling in old ways. (23)

So what are the causal ideas expressed here?

The factors Mann singles out here are decidedly macro-level:

war
class conflict and economic depression
rapid transition to democratic nation-states
cultural impressions of decay

These are high-level social conditions involving military power, economic power, political power, and cultural realities. Perhaps not surprisingly, these factors correspond to the main legs of Mann's own theory of social power: "My earlier work identified four primary 'sources of social power' in human societies: ideological, economic, military, and political" (5).

So the causal factors identified here are clearly at the macro level. The outcome Mann identifies is equally macro-level: the advent of fascist movements and governments in a handful of major European states. So the basic claim here is a macro-macro causal claim.

The causal claims expressed in the paragraph can be summarized in this way:

Factors F1, F2, F3, F4 each played a causal role in the rise of fascism
Factors F1, F2, F3, F4 each weakened (caused) the capacity of elites to continue to rule

What is the meaning of the idea that "F1 played a causal role in the rise of fascism"? Most simply, it is the notion that the factor occupies a position in the full causal diagram or causal narrative of the rise of fascism, beginning at some point in time. The action of hops in the process of brewing beer plays a causal role: many events and processes must occur in a timed sequence, but the activity of the hops is one necessary part of the overall process.

And how would an investigator piece together the causal narrative of a complex happening? It would appear that the method of "process tracing" is the most direct way of piecing together a causal narrative. This requires going through one or more empirical cases and probing the events that occurred to attempt to assess whether and how they played a causal role in the production of the outcome. This is exactly the form that Mann's investigation of the various fascisms of Europe takes; he examines the histories and tries to discern the causal sequences that are contained in them. (George Alexander and Andrew Bennett consider some of the challenges of this methodology in Case Studies and Theory Development in the Social Sciences.)

To say that a condition is a cause of a given outcome expresses as well the idea that the condition is either necessary or sufficient for the outcome; the presence or absence of the condition makes a difference for the occurrence of the outcome. The appearance of the cuckoo is neither necessary nor sufficient for the chiming of the clock; so the cuckoo is not a cause of the chiming. It would appear, then, that Mann is also committed to claims like this:

If war and depression had not occurred then fascism would not have prevailed in Italy
If Spain's democracy had been more solid and well established, then fascism would not have prevailed in Spain

Other causal ideas are suggested by the paragraph, even if not explicit:

War has the causal power to stimulate powerful social movements in combatant countries.
Widespread economic depression has the causal power to stimulate class antagonism.
Ideologies have the causal power to stimulate mobilization of adherents.
Ideologies of cultural decay have the power to weaken the capacity of elites to govern.

How do these ideas about causal powers flesh out in detail? How does "war" possess a causal power? War encompasses a complex set of circumstances and interlocking organizations: mobilization and demobilization of mass armies, disruption of civilian production, massive damage to people and property, unusual stresses on governments, etc. And each of these circumstances in turn has consequences which ultimately influence the circumstances in which the mass home population finds itself. Those home circumstances in turn play into the factors that are known to stimulate and amplify social movements -- popular grievances about government, economic deprivation, a general environment of uncertainty, and the availability of entrepreneurial leaders and organizations prepared to take advantage of these conditions. So war has a causal power that is embodied by the social, economic, demographic, and political circumstances that accompany it; and that power is expressed through influence on the home population.

One way of encapsulating this kind of story about the causal powers of a structural circumstance is to say that the circumstance conditions and motivates actions by many individuals in ways that lead to a certain class of outcomes. So the causal power story is also a Coleman's Boat kind of story; it is a specification of the microfoundations of the causal power in question. However, once we have satisfied ourselves about the microfoundations, we are not compelled to retrace our steps through the individual level in order to move the argument from Italy to Spain. We can rely on the idea that war has a given set of causal powers on macro outcomes in the next case in which we observe war and disorder.

Social hierarchy and popular culture

2012-05-01T19:40:00.000-04:00

There is some interesting work being done on the sociology of taste these days. I'm thinking specifically of a literature that has developed around the idea of "omnivorousness" and social status. Richard Peterson initiated much of this discussion in 1992 with an article in Poetics entitled "Understanding Audience Segmentation: From Elite and Mass to Omnivore and Univore" (link).

Between World Wars I and II it was widely accepted in intellectual circles that the emerging mass media were spawning an equivalent mass audience, an audience that was unthinking, herd-like, and inherently passive yet easily swayed by skilled political and commercial demagogues. (243)

But, Peterson claims, empirical research in communications does not bear this out; instead, the audience has differentiated into multiple audiences. The simple model of a "highbrow discerning elite with well-refined tastes and ... an ignorant and stimulus-seeking mass" (244) has been discredited. In other words, the simple theory of status that postulates that elites can be identified by a set of uniform refined cultural tastes does not hold up.

The hallmark of those at the top of the hierarchy according to the received elite-to-mass theory is patronizing the fine arts, displaying good manners, wearing the correct cut of clothes, using proper speech, maintaining membership in the 'better' churches, philanthropic organizations and social clubs, and especially for the women of the class, cultivating all of the attendant social graces. (245)

But, according to Peterson, this assumption can be tested, and it turns out to be incorrect. Peterson and other collaborators (Albert Simkus in particular) used social data sets to examine the distribution of preferred music styles across occupational groups arranged from high status to low status. Their status hierarchy of occupational groups ranges from "higher cultural" -- architects, lawyers, clergymen, and academics, to farm laborers. And the musical genres include a list of 10 types of music, ranging from classical to country. Here is one of the central findings:

The data presented in table 4 do not show this clear pattern of aesthetic exclusivity. Indeed, the occupational groups at the top are more likely to be high on liking these non-elite forms while the occupational groups at the bottom are likely to be low on their rate of liking them. Only one category of music, country and western, fits the predicted pattern, while three groups, mood music, big band, and barber shop music, show just the opposite of the predicted ranking. (249)

Based on these findings, Peterson recommends junking the "elite culture-mass culture" distinction in favor of an "omnivore-univore" distinction. There is indeed a significant difference in the cultural tastes of high-status and low-status people; but it doesn't correspond to the elite-mass distinction previously postulated.

Peterson and Kern's "Changing Highbrow Taste: From Snob to Omnivore" (ASR 1996, link) carries this line of thinking forward. Here is how Peterson and Kern begin their article:

Not only are high-status Americans more likely than others to consume fine arts, but, according to Peterson and Simkus (1992), they are are also more likely to be involved in a wide range of low-status activities. This finding ... flies in the face of years of historical research showing that high-status persons shun cultural expressions that are not seen as elevated.... In making sense of this contradiction, Peterson and Simkus (1992) suggest that a historical shift from highbrow snob to omnivore is taking place. (900)

"Snob" is defined as a person who does not like a single form of lowbrow or middlebrow activity, and "omnivore" is open to at least one such activity. Here are the lowbrow activities they track: country music, bluegrass, gospel, rock, and blues (901), and the defining highbrow arts activities they select are classical music and opera. Their empirical finding is that highbrows have increased their "omnivorousness" by about half a genre in a ten-year period of time from 1982 to 1992, from 1.74 lowbrow genres to 2.23 lowbrow genres (902).

They ask the natural question, what are some of the causes of this marked change during these years? And they put forward five factors; "in concluding we speculatively suggest five linked factors that may contribute to the shifting grounds of status-group politics" (905). They cite structural changes in society (broader education and exposure to the media, for example); value changes (declining levels of racial exclusion and stereotype); art-world changes (decline of elitist theories of art, rising appreciation of non-elite art forms); generational politics (the rock'n'roll generation); and status-group politics (gentrification of "lower-class" artistic forms).

This research is interesting in several ways. First, it is a statistically sophisticated attempt to observe the distribution of cultural tastes across a population and across time. The statistical analyses in the two studies allow Peterson and his collaborators to sort through issues about within-cohort and across-cohort taste changes. So this permits a more nuanced observation of a shifting social reality. And second, it arrives at what appears to be a statistically sound finding -- that highbrows were broadening their cultural tastes during the decade observed. Highbrows became less snobbish.

So this literature provides some tools for observing and measuring the prevalence and shifts of things that seem highly subjective -- musical tastes, in this instance. And it suggests some ways of formulating and evaluating hypotheses about the factors that explain the observed distributions and changes.

This literature pays explicit homage to Bourdieu's theorizing about taste in his Distinction: A Social Critique of the Judgement of Taste, originally published in 1979 in French. But the thrust of Bourdieu's work seems to be quite different from Peterson's. Bourdieu does indeed seem to believe that there are some very specific cultural markers that identify the elite class in society. He finds that one social group, the petite bourgeoisie, is indeed "omnivorous" in at least one sense: "Uncertain of their classifications, divided between the tastes they incline to and the tastes they aspire to, the petit bourgeois are condemned to disparate choices ... ; and this is seen as much in their preferences in music or painting as in their everyday choices" (326). But this statement seems to reproduce the elite-mass paradigm that Peterson rejects, in that it seems to position the tastes of the petit bourgeoisie intermediate between elite and mass tastes.

Here is a fascinating and complex graph Bourdieu provides mapping cultural items against occupational groups (higher-ed teachers, engineers, secondary teachers, industrial employers, etc.).

Dewey on habits

2012-04-30T05:41:00.000-04:00

I've sought here to discover some of the origins of current neo-pragmatist theories of the actor. John Dewey's writings are certainly crucial for that quest. So what did Dewey contribute to a pragmatist understanding of how people act? one place to look for an answer is in a 1922 book, HUMAN NATURE AND CONDUCT: An Introduction to Social Psychology. It is a particularly interesting book to read, in that Dewey goes back and forth between a kind of descriptive psychology and some astute theorizing about morality as a constraint on action.

A particularly central part of Dewey's theory of action is the idea of habit. He believes that a large volume of our ordinary human conduct is not deliberative or plan-ful at all, but is rather based on habit. So what is habit? Here is a brief description in Human Nature and Conduct:

Habit means special sensitiveness or accessibility to certain classes of stimuli, standing predilections and aversions, rather than bare recurrence of specific acts. It means will. (kl 386)

The word habit may seem twisted somewhat from its customary use when employed as we have been using it. But we need a word to express that kind of human activity which is influenced by prior activity and in that sense acquired ; which contains within itself a certain ordering or systematization of minor elements of action ; which is projective, dynamic in quality, ready for overt manifestation; and which is operative in some subdued subordinate form even when not obviously dominating activity. (Kindle Locations 378-381)

In the tradition of deliberative rationality, the idea of will is central. The agent deliberates about ends and means and chooses (wills) a means that will bring about her ends. So the will is the fundamental element of action. But in fact, Dewey argues that the idea of "will" itself can be understood as a compound of habits, rather than a self-originating deliberation about ends and means.

By will, common-sense understands something practical and moving. It understands the body of habits, of active dispositions which makes a man do what he does. Will is thus not something opposed to consequences or severed from them. (Kindle Locations 403-404)

Dewey's discussion of habit and action is particularly sensitive to the relationship between the constraints and practices of the body and human patterns of action. He uses an extended example of "standing straight", and points out that "good posture" is a complex characteristic involving the environment, the body, and the will. But crucially, the unadorned will ("I will henceforth stand straight") cannot in fact determine subsequent behavior. In fact, he argues that the idea of standing straight can only come to us once we are bodily capable of good posture:

Only the man who can maintain a correct posture has the stuff out of which to form that idea of standing erect which can be the starting point of a right act. (Kindle Locations 302-303)

Given a bad habit and the " will " or mental direction to get a good result, and the actual happening is a reverse or looking-glass manifestation of the usual fault-a compensatory twist in the opposite direction. Refusal to recognize this fact only leads to a separation of mind from body, and to supposing that mental or " psychical" mechanisms are different in kind from those of bodily operations and independent of them. (Kindle Locations 312-314)

He also emphasizes the point that habits in action generally presuppose a social context:

But since habits involve the support of environing conditions, a society or some specific group of fellow-men, is always accessory before and after the fact. Some activity proceeds from a man; then it sets up reactions in the surroundings. Others approve, disapprove, protest, encourage, share and resist. (Kindle Locations 167-169)

Or in other words, we acquire our habits of behavior through exposure to other actors.

We often fancy that institutions, social custom, collective habit, have been formed by the consolidation of individual habits. In the main this supposition is false to fact. To a considerable extent customs, or wide-spread uniformities of habit, exist because individuals face the same situation and react in like fashion. But to a larger extent customs persist because individuals form their personal habits under conditions set by prior customs. (Kindle Locations 523-525)

This is a point made elsewhere in the blog in the context of the idea of methodological localism: the individual takes shape through the persistent fact of existing social practices and norms. Here is a representative example of Dewey's ideas about the social construction of the individual.

We come back to the fact that individuals begin their career as infants. For the plasticity of the young presents a temptation to those having greater experience and hence greater power which they rarely resist. It seems putty to be molded according to current designs…. Education becomes the art of taking advantage of the helplessness of the young; the forming of habits becomes a guarantee for the maintenance of hedges of custom. (Kindle Locations 571-573)

Moreover, individual habits in turn contribute to social patterns:

Our individual habits are links in forming the endless chain of humanity. Their significance depends upon the environment inherited from our forerunners, and it is enhanced as we foresee the fruits of our labors in the world in which our successors live. (Kindle Locations 207-209)

And habits are the foundation of ethical ideas as well:

Education becomes the art of taking advantage of the helplessness of the young; the forming of habits becomes a guarantee for the maintenance of hedges of custom. (Kindle Locations 578-579)

So the fact of habit in action is in fact a very fundamental part of Dewey's view of the social world and the individual actor's role in that world. And it is a role that suggests that Dewey differs very fundamentally from the Aristotelian view of deliberative rationality in action, where the actor identifies a set of ends, arrives at a set of beliefs, and reasons to a conclusion about what action to choose. (It seems to have more in common with another aspect of Aristotle's theory of action, the role that virtue plays in ordinary conduct.) Dewey doesn't say that there is nothing deliberative about action; but he appears to believe that habit is more common and more fundamental; further, he seems to believe that many examples of the exercise of will are in fact examples of the influence of nested sets of habits. Dewey seems to accept this implication about the subordinacy of reasoning to habit:

Habit, occupation, furnishes the necessity of forward action in one case as instinct does in the other. We do not act from reasoning; but reasoning puts before us objects which are not directly or sensibly present, so that we then may react directly to these objects, with aversion, attraction, indifference or attachment, precisely as we would to the same objects if they were physically present. (Kindle Locations 1724-1726)

This component of a theory of action seems valid with respect to a range of human behaviors and interactions, but it seems to seriously undervalue the fact of conscious deliberation in action. It cannot be denied that human actors do sometimes approach problems of action -- what to do? -- in a conscious and deliberative way. This is the kernel that underlies rational choice theory, and it seems to be a plain and undeniable part of human problem solving and choice. Dewey's understanding of action as the result of an ensemble of socially instilled habits seems in the end to be unsatisfactory as a full theory of action.

Actor-centered sociology

2012-04-25T22:11:00.000-04:00

I've advocated many times here for the advantages of what I've referred to as "actor-centered" sociology. Let's see here whether it is possible to say fairly specifically what that means. Here is an elliptical description of three aspects of what I mean by "actor-centered sociology":

First, it reflects a view of social ontology: Social things are composed, constituted, and propertied by the activities and interactions of individual actors -- perhaps 2, perhaps 300M. Second, it puts forward a constraint on theorizing: Our social theories need to be compatible with the ontology. The way I put the point is this: social theories, hypotheses, and assertions need microfoundations. Third, "actor-centered sociology" represents a heuristic about where to focus at least some of our research energy and attention: at the ordinary processes and relations through which social processes take place, the ordinary people who bring them about, and the ordinary processes through which the effects of action and interaction aggregate to higher levels of social organization.

(a) This means that sociological theory need to recognize and incorporate the idea that all social facts and structures supervene on the activities and interactions of socially constructed individual actors. It is meta-theoretically improper to bring forward hypotheses about social structures that cannot be appropriately related to the actions and interactions of individuals. Or in other words, it means that claims about social structures require microfoundations.

(b) The meta-theory of actor-centered sociology requires that all social theories, at whatever level, require a theory of the actor. Economics and ethnomethodology differ in the level of specificity they offer for their theories of the actor; but both have such a theory. They both put forward fundamental ideas about how actors think and the mental processes that influence their actions.

(c) Actor-centered sociology suggests that careful study of local social mechanisms and behaviors is a worthwhile exercise for sociological research. Ethnomethodology and the careful, place-based investigations offered by Goffman and Garfinkel move from the wings to the stage itself.

(d) It appears to imply that we may be able to provide an explanation of at least some higher-level social facts by showing how they emerge as a result of the workings of actors and their structured interactions. This is the aggregation-dynamics methodology (link). Or in terms discussed elsewhere here, it is the micro-to-macro link of Coleman's boat (link).

(e) The actor-based sociology approach seems to imply that the regularities that may exist at the level of macro-social phenomena are bound to be weak and exception-laden. Heterogeneity within and across actors -- across history and across social settings -- seems to imply multiple sets of attainable aggregate outcomes. Would fascist organizations flourish in Italy after World War I? The answer is indeterminate. There were numerous groups of social actors with important differences in their states of agency, and these groups in turn were influenced by organizations of varying characteristics. So it would be impossible to say in advance with confidence either that fascism was likely to emerge or that it was unlikely to emerge (link).

(f) The actor-centered approach suggests that we can do better sociology by being more attentive to subtle differences in agency in specific groups and times. George Steinmetz's careful attention to the processes of formation through which colonial administrators took shape in nineteenth-century Germany illustrates the value of paying attention to the historical particulars of various groups of actors, and the historically specific circumstances in which their frames of agency were created (link). It implies that context and historical processes are crucial to sociological explanation.

(g) The actor-centered approach highlights the importance of careful analysis of the mechanisms of communication and interaction through which individuals influence each other and through which their actions aggregate to higher level social outcomes and structures. Social networks, competitive markets, mass communications systems, and civic associations all represent important inter-actor linkages that have massively important consequences for aggregate social outcomes.

(h) Finally, the actor-centered approach has some of the advantages of the spotlight in a three-ring circus. The idea of actor-centered sociology points the spotlight to the parts of the arena where the action is happening: to the formation of the actor, to the concrete setting of the actor, to the interactions that occur among actors, to the aggregative processes that lead to larger outcomes, and to the causal properties that those larger structures come to have.

One thing that is somewhat troubling for anyone who has been reading this blog over time is that there seems to be a glaring inconsistency in two lines of thought emphasized repeatedly here: first, that social facts require microfoundations; and second, that meso-structures can have autonomous causal properties. Are these two ideas consistent?

In particular, one might interpret the imperative of actor-centered sociology as a particularly restrictive view of social causation: from configurations of actors to meso-level social facts. So all the causal "action" is happening at the level of the actors, not the structures. Dave Elder-Vass attempts to avoid this implication by arguing for emergent social causal properties (link); I've approached the problem by talking about relatively autonomous causal properties at the meso-level (link). I continue to think the latter view works reasonably well. In a post on "University as a causal structure," for example, I think a plausible case is made for both ideas: the tenure system is causally effective in constraining individual faculty members' behavior as well as being causally effective in influencing other structural features of the university; and every aspect of this system has microfoundations in the form of the structured circumstances of action and culturation through which the bureaucratic agents in the system behave. Or in other words: it is consistent to maintain both parts of the dilemma, actor-centered sociology and relatively autonomous meso-level social causation (link).

Recent historiography of China

2012-04-22T22:01:00.000-04:00

The field of China history evolved rapidly after the McCarthy attacks on the field in the 1950s. The most significant developments, in my view, are these. First, there developed in the 1960s and 1970s what Paul Cohen refers to as a “China-centered” approach to the study of the history of China (Discovering History in China: American Historical Writing on the Recent Chinese Past; 1984). The central notion here is the idea that historians of China need to analyze China’s history making use of concepts and hypotheses specific to its own experience. Cohen puts the point this way: “The main identifying feature of the new approach is that it begins with Chinese problems set in a Chinese context. . . . [These] are Chinese problems, in the double sense that they are experienced in China by Chinese and that the measure of their historical importance is a Chinese, rather than a Western, measure” (Cohen 1984, p. 154). Rather than asking whether China experienced “sprouts of capitalism” in the Ming Dynasty, we need to consider the distinctive features of China’s economic development. Rather than considering whether China was a “feudal” society, we need to identify and conceptualize the specific features of political and economic relations that linked elites and the common people.

The point here is not that China’s history is unique and sui generis, but rather that one should not presume that the categories of politics, social structure, and historical process that emerged as central in the unfolding of early modern Europe will find natural application in the historical experience of China. The concept of feudalism is not a trans-historical category which should be expected to have application in every process of historical development. Bin Wong pushes this view further in his China Transformed: Historical Change and the Limits of European Experience.

Second, there has emerged a substantial emphasis on material culture in the China field: social and economic circumstances, the technology of agriculture, marketing hierarchies, and the circumstances of life of ordinary Chinese people. Features of local material culture find prominent expression: population processes, local politics, agricultural technique, land tenure arrangements, patron-client relations, banditry, and environmental change. And since historical China is an agrarian society, this means that agrarian histories have been particularly important in the China field. (Here is a post on China's agricultural history; link.)

Third, China studies have moved in the direction of local or regional studies rather than national histories. Issues arising out of consideration of the village rather than the capital city have come to the fore: the village, the marketing hierarchy, and the region have come to define the focus of inquiry. Scholars are suspicious of generalizations about China as a whole; rather, local and regional variations are the focus of research. It is recognized that lineage is more significant in the south of China than the north; that rice cultivation imposes a series of social imperatives in the south that are absent in the north; that regions linked by water transport show an economic and social integration often lacking in administratively defined units (provinces); that millenarian Buddhism is a powerful factor in the political culture of Shandong but not in Sichuan; and the like. Huaiyin Li's Village China Under Socialism and Reform: A Micro-History, 1948-2008 is a good example of this kind of detailed local study.

Finally, the influence of the social sciences in the field of Chinese history has been of great importance. Much (though of course not all) of the most productive historical research on China in the past two decades has made substantial use of the tools of social science to construct explanations of Chinese historical processes. Techniques drawn from historical demography, economic geography, and the study of organizational behavior have substantially increased our understanding of China’s history. Work by James Lee and numerous collaborators on China's demographic history provide good examples of the fruitfulness of this approach; Life under Pressure: Mortality and Living Standards in Europe and Asia, 1700-1900 (Eurasian Population and Family History).

Here are a few topic areas that have proven to be particularly important.

Spatial organization of culture and economy. China studies have been strongly influenced by the insight that there is a critical spatial dimension to processes of social, political, and economic change. In his groundbreaking work on marketing hierarchies and the regionalization of traditional China, G. William Skinner has demonstrated the key role that transport systems, central place hierarchies, and physiography play in China’s history (link, link.) Skinner’s work has been remarkably influential in the China field; among his contributions, two are especially important. First, Skinner undercut the village-oriented perspective of much existing research on peasant China by putting forward an analysis of the central place hierarchy that exists among cities, market towns, villages, and hamlets in traditional China (Skinner, G. William. 1964-65. "Marketing and Social Structure in Rural China." Journal of Asian Studies 24(1-3)). These hierarchies are knit together by transport systems and the circulation of products, traders, craftsmen, martial arts instructors, necromancers, and other itinerant folk. This is an important contribution because it suggests stimulating hypotheses about the mechanisms of popular culture, the transmission of ideas, the movements of peoples, the diffusion of new technologies, and other fundamental aspects of social change. The second signal contribution contained in Skinner’s work is his regionalization of China into nine “macroregions,” each of which is analyzed in terms of a core-periphery structure (The City in Late Imperial China; 1977). This construct incorporates the structure of marketing hierarchies into the analysis and adds the notion that the economic processes implicit in urbanization impose a structure on rural society as well. Urban cores create a demand for resources (firewood, food, raw materials) that extend economic influence into peripheral areas.

These ideas have a number of important implications for agrarian studies more generally. First, the spatial organization of settlements--villages, towns, and cities, and the transport and marketing networks that connect them--has important consequences for diverse aspects of rural life. Ideas, political movements, and knowledge are diffused through marketing system channels. Itinerant merchants, artisans, letter writers, necromancers, fortune-tellers, or martial-arts instructors travel the circuits defined by the marketing hierarchies; and through these travelers results movement of ideas, products, rumors, skills, and innovations.

Environmental history. There are numerous examples of recent works that give central focus to environmental and ecological issues in China’s history. Environmental issues come in a number of forms in Chinese history, including especially water management, land reclamation, and deforestation. As Skinner points out, there is a strongly spatial orientation to each of these sets of issues: water systems constitute one of the lineaments determining patterns of settlement; land reclamation and deforestation follow population density (and therefore tend to correspond to a core-periphery structure, with a transfer of fertility from periphery to core).

An important treatment of the human impact on the Chinese environment is Peter Perdue’s study, Exhausting the Earth: State and Peasant in Hunan (Perdue 1987). Perdue’s study focuses on Hunan, 1500-1850, and places primary emphasis on the processes of agricultural change, land reclamation, and water control through which the landscape of Hunan was dramatically altered throughout this period. The struggle between the state and local interests over such issues as taxation, land reclamation, dike building, and land property rights is highlighted. What is most original about the book is Perdue's success in identifying the consequences for ecology and land and water management of the political and economic processes involved in Hunan’s substantial growth during this period. Perdue documents the slow process through which land reclamation efforts and dike-building nibbled away at Dongting Lake (now China’s second largest lake). The state played an important role in stimulating this process in the Ming dynasty; in the Qing, Perdue indicates that the private interests of local elites and landowners were the driving force for continuing encroachment on wetland and lake margins.

More recently Mark Elvin’s The Retreat of the Elephants: An Environmental History of China provides a broad treatment of China’s environmental history over a longer and broader scope (link).

State-society relations. State-society relations play an important role in many contemporary studies: to what extent, and through what mechanisms, is the state in a pre-modern society able to effect its will on its population? This question is particularly salient in the case of China because of the somewhat paradoxical role that the Imperial state plays in Chinese history. The Imperial system is often portrayed as weak and ineffectual; at the same time, it is the embodiment of a refined and sophisticated administrative apparatus. To what extent was the Chinese state able to carry out its essential functions--the extraction of taxes, the preservation of order, the suppression of social unrest, the maintenance of large-scale water projects, and the administration of central grain policies? These issues impact on agrarian histories in diverse ways: mobilization of peasant unrest is affected by the extractive behavior of the state, on the one hand, and the effectiveness of the state’s coercive apparatus, on the other.

In Rebellion and its Enemies in Late Imperial China: Militarization and Social Structure, 1796-1864 Philip Kuhn emphasizes the limitations of the grasp of the imperial state in his analysis of the local and regional responses to the Taiping Rebellion. “Local militarization posed acute problems for the imperial state; for if irregular military force could not be regularized and brought under control, if the widespread militarization of local communities could not be brought into a predictable relationship to the state, then the security of the state itself might soon be shaken” (Kuhn 1980, p. 9). There was a logic to the process of the state’s diminishing capacity to effect its will in response to rebellion. “The Ch'ing military establishment lent momentum to the downward spiral of dynastic decline: the worse the troops, the longer it took them to quell an uprising; the longer it took them, the greater the cost; the more impoverished the government, the lower the quality of imperial administration and the greater the frequency of revolt” (126). On Kuhn’s interpretation, the local militarization that occurred in response to the Taiping Rebellion had a permanent effect on the balance of power between center and periphery in Chinese politics.

In his study of state-society relations in North China, Culture, Power, and the State: Rural North China, 1900-1942 (1988), Prasenjit Duara emphasizes the “state-making” processes that were underway in the late Qing. Duara’s analysis focuses on the end of the Qing dynasty and the turn of the twentieth century in North China; Duara attempts to comprehend the variety of institutions, elites, and influences through which political power was wielded at the village level. The state was earnest in its efforts to penetrate rural society to the village level, and Duara examines the efforts made to extend the administrative structures of the state into the system of lineage and local power relations which had traditionally dominated village society.

Intermediate between studies of the Imperial state and local agrarian histories is the effort to discern the “patterns of dominance” exercised by Chinese local elites (Esherick and Rankin, eds., Chinese Local Elites and Patterns of Dominance, 1990). Studies by Keith Schoppa, Mary Rankin, Phillip Kuhn, and William Rowe provide instances of in-depth efforts to identify the historical identities of Chinese elites, rural and urban, and some of the mechanisms through which these elites endeavored to influence local society.

The core-periphery analysis mentioned above has been found fruitful as well in analysis of banditry, rebellion, and smuggling. The grasp of the state tends to be weakest in peripheral areas with difficult terrain (mountains, deserts, marshes), sparse settlement, and poor transport networks; and consequently anti-state activities find natural refuge in such areas.

Vivienne Shue's The Reach of the State: Sketches of the Chinese Body Politic is an important contribution to this topic.

Other topics. Most recently the China field has been interested in the “involution” debate, culminating in Huang (The Peasant Family and Rural Development in the Yangzi Delta, 1350-1988), Pomeranz (The Great Divergence: China, Europe, and the Making of the Modern World Economy.), and Wong and Rosenthal (Before and Beyond Divergence: The Politics of Economic Change in China and Europe) (link, link, link). And, of course, there is a very large historiography of the Chinese Revolution and the Cultural Revolution. Several earlier posts provide discussion of post-1960s treatments of the Chinese Revolution; link, link.

These topics are certainly not exhaustive. I've said nothing here about cultural and identity studies; studies of ethnic minorities in China; popular culture; and much else. But the field is large, and it is worthwhile for the non-specialist to have at least a rough map of some of the large pathways explored in the past forty years as historians have sought to make better sense of China's history.

George Herbert Mead on the self

2012-04-19T23:19:00.002-04:00

Sociologists sometimes come back to George Herbert Mead as a founder who still has something important to contribute to contemporary theory. This is especially true in ethnomethodology and symbolic interactionism, but it comes up in current lively discussions of pragmatism and action as well. So what can we learn from reading Mead today?

Mead writes and thinks in a way that is both scientific and philosophical. His contributions are to the field of "social psychology," and he locates himself within a discourse that includes Watsonian behaviorism and William James's introspectionism. But much of his prose seems very familiar to me as a philosopher. You can hear the reverberations of earlier philosophical debates in his writing -- Cartesianism, Hegelianism, Dilthey's hermeneutics -- and his style of argumentation also feels philosophical. (I never read Mead during my training as a philosopher, though the pragmatist spirit surely infused the Harvard philosophy department, with its intellectual affiliations to James and Peirce.)

Let's take a quick tour through some of the topics in Mind, Self, and Society: From the Standpoint of a Social Behaviorist (Works of George Herbert Mead, Vol. 1). The title is entirely descriptive; the core issue is how to characterize the "me" -- the personal, the conscious individual, the intentional actor, and to theorize about how the self is related to the social world. Mead's fundamental view is that the tradition of philosophy has gotten the relationship backwards; philosophers have built the social from the individual, but actually the self is in some important way the sum of its social relations.

The difference between the social and the individual theories of the development of mind, self, and the social process of experience or behavior is analogous to the difference between the evolutionary and the contract theories of the state as held in the past by both rationalists and empiricists. The latter theory takes individuals and their individual experiencing—individual minds and selves—as logically prior to the social process in which they are involved, and explains the existence of that social process in terms of them; whereas the former takes the social process of experience or behavior as logically prior to the individuals and their individual experiencing which are involved in it, and explains the existence in terms of that social process. (222).

Mead favors the "social first" approach. This doesn't rest on some kind of spooky Durkheimianism about irreducible social wholes, but rather the point that individuals always take shape within the ambit of a set of social relationships, language practices, and normative cues.

Our contention is that mind can never find expression, and could never have come into existence at all, except in terms of a social environment; that an organized set or pattern of social relations and interactions (especially those of communication by means of gestures functioning as significant symbols and thus creating a universe of discourse) is necessarily presupposed by it and involved in its nature. (222)

Mead's theory postulates that the self is built up out of imitative practices, gestures, and conversations over time. The individual forms a reflective conception of his / her self that derives from example and engagement with specific other actors within his / her social space. Here is how he puts his theoretical stance in the first few pages:

I have been presenting the self and the mind in terms of a social process, as the importation of the conversation of gestures into the conduct of the individual organism, so that the individual organism takes these organized attitudes of the others called out by its own attitude, in the form of its gestures, and in reacting to that response calls out other organized attitudes in the others in the community to which the individual belongs. This process can be characterized in a certain sense in terms of the “I” and the “me,” the “me” being that group of organized attitudes to which the individual responds as an "I". (185)

One thing that makes Mead's position here more distinctive is the way that it fits into his broader theory of symbolic manipulation. His ideas about rationality rotate around the human being's ability to use and manipulate symbols. This is what reflective thought involves, according to Mead: to assign symbols to features of he world, and then to choose actions based on reasoning about the relationships among those symbols.

Here is another clear statement about the self and the social:

The mind is simply the interplay of such gestures in the form of significant symbols. We must remember that the gesture is there only in its relationship to the response, to the attitude. (188)

This insistence on the primacy of social relationships for defining the self might imply a problem for the first human self; but actually the development of sociality presumably parallels exactly the development of language and action. We aren't forced to begin in a social contract, state of nature point of view.

So what do action and intention look like on Mead's approach? He asks the question, what role does thought play in action? He concludes that it does play a role; but that the role is not entirely inside the head. His example turns the rational actor model on its head. Rather than deriving outcomes from the bare calculating actor, he understands the actor's deliberations in terms of the values and attitudes of his/her social environment. Speaking of a hypothetical policy maker who identifies strongly with his/her community, he writes:

He is successful to the degree that the final “me” reflects the attitude of all in the community. What I am pointing out is that what occurs takes place not simply in his own mind, but rather that his mind is the expression in his own conduct of this social situation, this great co-operative community process which is going on. (187)

And here is a nice description of purposive action.

In the type of temporary inhibition of action which signifies thinking, or in which reflection arises, we have presented in the experience of the individual, tentatively and in advance and for his selection among them, the different possibilities or alternatives of future action open to him within the given social situation—the different or alternative ways of completing the given social act wherein he is implicated, or which he has already initiated. (90)

This is a reasonable statement of the situation of purposive deliberation: the person entertains in thought the various behaviors he/she can undertake and the possible consequences of those behaviors. The person then chooses a behavior in consideration of which of those consequences is most favored. So this passage conforms loosely to the desire-belief-outcome model and provides an explication of an aspect of consciousness and reflexivity. What is perhaps somewhat more surprising, however, is that Mead's position here seems mildly inconsistent with the earlier expressed ideas of the self as a reflection of the social world in which the biological individual abides. This passage suggests more of a traditional individual-rationality approach to action.

Another common thread in Mead's various discussions of action and behavior is his use of the idea of "habit". Mead places "habit" as an alternative to "intelligent conduct":

It is the entrance of the alternative possibilities of future response into the determination of present conduct in any given environmental situation, and their operation, through the mechanism of the central nervous system, as part of the factors or conditions determining present behavior, which decisively contrasts intelligent conduct or behavior with reflex, instinctive, and habitual conduct or behavior—delayed reaction with immediate reaction. That which takes place in present organic behavior is always in some sense an emergent from the past, and never could have been precisely predicted in advance—never could have been predicted on the basis of a knowledge, however complete, of the past, and of the conditions in the past which are relevant to its emergence; and in the case of organic behavior which is intelligently controlled, this element of spontaneity is especially prominent by virtue of the present influence exercised over such behavior by the possible future results or consequences which it may have. (98)

He turns to the concept of habit to explain language and to describe ordinary actions in the world.

One of the most interesting currents in sociology today is the new pragmatism -- I'm thinking of work by Neil Gross and Hans Joas in particular. Several earlier posts have focused on their efforts to provide a new theory of the actor that draws upon pragmatism (link, link). Mead's theory of the self provides some of the intellectual foundations of this approach; but it doesn't tell the whole story. In particular, the provocative ideas that are foundational in the new pragmatism --

"focus on the action rather than the actor",
"action is a flow of improvisational adaptations", and
"action is relational rather than individual"

-- seem not to originate in Mead. Mead's central contributions (in a Twitter-sized bite) seems to be that the self is constituted and created by its social context; and there is a large component of "habit" in ordinary social action.

The market for ethnicity

2012-04-17T19:15:00.002-04:00

John Comaroff and Jean Comaroff have written a complex story of contemporary ethnicity and culture in Ethnicity, Inc.. The Comaroffs are, of course, distinguished cultural anthropologists at the University of Chicago who have done extensive research and writing on Africa. (For example, John Comaroff and Simon Roberts, Rules and Processes: The Cultural Logic of Dispute in an African Context; Jean Comaroff and John Comaroff, Of Revelation and Revolution, Volume 1: Christianity, Colonialism, and Consciousness in South Africa: 001.) So their observations on culture and ethnicity in a globalizing world are bound to be interesting.

Here is a nice statement of the way they conceptualize "ethnicity" (referring to Ethnography And The Historical Imagination):

For our own part (e.g., Comaroff and Comaroff 1992:49- 67), we have long argued that ethnicity is neither a monolithic "thing" nor, in and of itself, an analytic construct: that "it" is best understood as a loose, labile repertoire of signs by means of which relations are constructed and communicated; through which a collective consciousness of cultural likeness is rendered sensible; with reference to which shared sentiment is made substantial. (kl 542)

So ethnicity is semiotic and labile -- or in other words, it consists in socially shared expressions of meaning, and it is especially prone to change and adaptation.

Their central focus in this short book is on ethnicity marketized -- hence "Ethnicity, Inc." Here is the heart of their insight in the book:

While it is increasingly the stuff of existential passion, of the self-conscious fashioning of meaningful, morally anchored selfhood, ethnicity is also becoming more corporate, more commodified, more implicated than ever before in the economics of everyday life. To this doubling--to the inscription of things ethnic, simultaneously, in affect and interest, emotion and utility--is added yet another. (kl 18)

They document in detail the central idea expressed by the title; the idea that ethnic groups worldwide are looking to commercialize and commodify their indigenous cultures. Even Scotland is looking to brand and market itself -- along with the Shipibo of Peru, MEGA of Kenya, and Contralesa in South Africa. And, of course, this process throws a big handful of sand into the gears of the idea of "cultural authenticity" itself (post). The commodification of ethnic identity to which they refer is illustrated with many examples; for instance, with snippets from marketing materials developed for some of the world's ethnic groups.

Experience the Shipibo Way of Life for yourself in the heart of the Amazon Basin with our Peru Eco-Tourism adventure! Learn how to make Shipibo ceramic artwork, go spear fishing in the Amazon river and much, much more. (the Shipibo Home page from Amazonian Peru (disappeared))

The "identity" sector of the North Catalonian' economy represents a new openmindedness [that] will see an expansion based on the culture of the region ... as an alternative to globalisation. (the North Catolonian web page (disappeared))

MEGA [Meru, Embu, Gikuyu, Gikuyu Association, Kenya] Initiative Welfare Society is a community organisation formed to foster social/ cultural and economic development of Ameru, Aembu and Agikuyu people of Kenya. It ... is driven by the desire to demonstrate how a community or a region can bring about prosperity by exploiting the cultural richness and entrepreneurial skills and resources of its people ... (MEGA Welfare Society Home Page (disappeared)) (kl 14-46)

And from South Africa they describe Contralesa:

The Congress of Traditional Leaders of South Africa (Contralesa) is the representative voice of ethnicity in the country. It speaks for culture, customary law, and the collective rights of indigenous peoples. Also for the authority of their chiefs and kings, past and present.... Having established a business trust a year earlier in order to join a mining consortium, they were about to create a for-profit corporation to pursue investment opportunities in minerals, forestry, and tourism; formal application had been made to register the company. (kl 77)

The second thread of argument they engage is the current political and philosophical literature on ethnicity and globalization. Discussing Foucault, Adorno, Montesquieu, and numerous others, they do some careful thinking about where "ethnic identity" stands now in philosophy and theory. They discuss, for example, the juridicalism that has swept through the field in human rights and first peoples (kl 789). (They refer generically to the effort to establish legal rights of property along ethnic lines as "lawfare"; kl 797.)

The commodification of ethnicity plays directly into the argument that identities are socially constructed and performative. The recreation of "traditional crafts, ceremonies, and dancing" in tourist villages is plainly a Disneyland kind of activity -- even when the performers have some hereditary relation to the earlier practices to which these reenactments point. The ersatz culture that is performed has little or no resonance with ordinary life in those current groups.

But it also appears that C&C also believe that people have identities as embodied subjectivities -- however labile and socially influenced they may be. And this implies that it is possible and worthwhile to investigate those subjectivities in their own terms.

There is a final pole to their analysis of ethnicity within the marketplace: the fact that ethnically defined groups are concerned about their property rights in a variety of things: traditional medications, historical land holdings, mineral resources, and even their languages. This reflects a point about power and politics: a group is more able to sustain itself as a coherent group when it is able to successfully establish rights in important resources. And these collective rights of ownership may play back into the mechanisms that support the persistence of a subjective group identity.

So it is that we return to where we began, with the articulation--the manifest expression, the joining together--of culture to property, past to future, being to business, entrepreneurialism to ethno-preneurialism. The permanent, unresolved, often aspirational dialectic that connects the incorporation of identity to the commodification of difference looks to be extending in all directions. (kl 2004)

What is unclear to me after reading the book is whether the two parts -- socially constructed performances for a paying public and persistent subjectivity -- are as closely connected as the Comaroffs seem to think. Here, in a nutshell, is how they think the two dynamics are connected:

What conclusions may be drawn from all this? Could it be that we are seeing unfold before us a metamorphosis in the production of identity and subjectivity, in the politics and economics of culture and, concomitantly, in the ontology of ethnic consciousness? (kl 279)

But are the two processes of identity-shift really so closely connected? Does the fact that economic development policy makers want to brand Scotland really tell us much about whether there is a "Scot identity"? What kind of theorizing and research do we need to do in order to take the measure do what it's like to be a Scot today? What might be included in such a status over a dispersed population of people with some historical ties to Braveheart? Is it a set of collective memories and monuments, a set of emotions of attachment to a standard narrative of Scottish history, or a set of behaviors, habits, and locutions?

In some way it seems as though the commodification of ethnicity is a sideshow, though an interesting one, while the real action is taking place elsewhere. (I don't doubt that they are right in judging that the performances the Shipibo people put on for ethno-tourists have a feedback effect on the ways they think about themselves, and therefore contributes to a degree of shift in the particulars of their ethnic identities.) But there is substantive ethnographic work to be done on the conceptualization and description of these forms of subjectivity themselves, and the ways in which they are influenced and transmitted over time. Marketization is part of that process -- but it is only one part. And it seems as though the marketing of ethnicity to tourists is a fairly special case.

Think of all the ethnic identities that are continuing to evolve and shift without any involvement of the kinds of commercialization of ethnicity that C&C focus on: the South Asian diaspora in the Midwest, the Burmese community in Minneapolis, the Jewish community in New Mexico or Shanghai. In each case there are complex dynamics of memory, cell phones, traditions adapted to new circumstances, remittances, family conversations, and dozens of other mechanisms through which dispersed communities are maintaining and morphing their ethnicities. There is certainly more to the dynamics of ethnicity in the contemporary world than the commodification that the Comaroffs single out.

(Earlier discussions of diasporic communities and methodological nationalism here and here focus on some of those dynamics.)

Race, perception, and reality

2012-04-14T09:50:00.001-04:00

Several recent themes come together in Ron Jacobs' very interesting 2000 book, Race, Media, and the Crisis of Civil Society: From Watts to Rodney King (Cambridge Cultural Social Studies). There is the recurring theme of racial separation in American society, this time with respect to divergent perceptions of important historical events. There is the role of representation and framing as a component of identity and agency. And there is the question of realism: given the fact of divergence, what sense can we make of the question, what really happened?

Jacobs is a cultural sociologist, within a group of theorists who believe that social imagination, representation, and framing are interesting and appropriate objects of sociological inquiry. Like theorists in the broad field of social mobilization, he believes that an understanding of these "subjective" features are key to understanding mobilization and action. But he also takes very seriously the idea that an individual's (or group's) mental framework is constructed by concrete social processes, including the media. And, finally, he offers a sophisticated framework in terms of which to analyze and dissect the media itself. This is an approach that blends the methods of the social sciences and the humanities in a very constructive way.

His specific goal in this book is to try to identify crucial differences of framework between African-American and white publics in the United States at several important junctures. He studies the African-American and mainstream press in their reporting of the Watts uprising (1965) and the disturbances that followed the Rodney King beating and court findings. The African-American press serves an important "fragmented public", and Jacobs wants to identify in detail the differences in perspective that exist between it and the mainstream press.

The theoretical frame for Jacobs is Habermas's thinking about communication, discourse, and the public sphere. He largely buys into Habermas's notion that a populace constitutes itself as a collective identity through discourse in public spaces. And the media represent some of those spaces. But he diverges from Habermas's views in emphasizing that there are multiple publics and multiple discourses. And this point is particularly important when it comes to race in the United States. The OJ Simpson trial illustrated this point very sharply, with widely divergent opinions about the trial among African-Americans and white Americans.

Jacobs' primary method is narrative analysis. He analyzes several thousand news stories with respect to plot, characters, and genres. And he finds there are substantial and consistent differences between mainstream and African-American press accounts of Watts, Rodney King, and the innocent verdicts for the police assailants of Rodney King.

What Jacobs doesn't assert, and what probably isn't true, is that the perspective found in, say, the Chicago Defender, is a faithful, exact expression of the collective perspective and framing of the black public of Chicago at a point in time. Rather, the Defender is a media publication with an editorial perspective and a small group of writers and editors. They have their own perspectives. As Jacobs points out, the Defender helps to influence black perspective in Chicago, but it isn't identical to the mentality of the black Chicago public or publics. (One might speculate that much of Chicago's black youth took a more radical and less patient view of police harassment than the Defender.) In order to probe these mentalities on the ground, a different kind of research would be needed -- ethnographic rather than documentary.

So this invokes one of the themes of realism we've surfaced in recent posts: what can we say about the truth of the matter when it comes to assertions about social perceptions and representations? And here I'm not thinking of the veridicality of the black teenager's perceptions of the police, but rather the veridicality of the sociologist's representations of that group's perceptual scheme about race and the police. How does critical realism come into the picture when we are discussing intangible, subjective features of imagination and representation by a social group? Can we be realists about mentalities?

I believe that the answer is "yes". There are research methods that permit a degree of confidence in assessing the forms of thinking associated with a given group at a given time. These range from participant-observer methods, to ethnography more broadly, to the kind of historical ethnography practiced by Robert Darnton, to survey methods attempting to measure attitudes and values. These methods generally require interpretive skills and judgments on the part of the investigator -- in this respect the sociologist is also a humanist--but it is reasonable to think that evidence-based inquiry can lead to reasonably confident conclusions about facts of subjectivity.

And this leads to another connection to realism: subjective schemes of interpretation are linked to actions as well. Mentality and action are linked. So the fact that Chicago teenagers in 1968 perhaps shared a narrative of police brutality very plausibly played a causal role in their behaviors in Chicago's uprising. So realism about the causes of contentious politics requires a degree of realism about mentalities as well.

(All of the action in Jacobs' book involves Los Angeles, a city with a very specific racial history. Readers will find the Easy Rawlins novels of Walter Mosley a vivid representation of African-American life in LA in the 1950s -- e.g. A Red Death (Easy Rawlins Mysteries). But even here a question of realism arises: can we gain realistic understanding of a historical moment through a novel? Does Mosley offer a true depiction of race in LA?)

Running on empty

2012-04-10T17:04:00.000-04:00

We've been focusing on the 1 percent and the 99 percent for the past year, thanks to the Occupy movement. But here's another way of slicing American society -- right down the middle. How is the 50 percent doing these days?

The answer seems to be, not very well. And the conservative assault on the social safety net pretty much guarantees that this part of American society will do even worse in the coming years. Poverty is concentrated in this half of America, both adult and child; the percentage of uninsured people is high; and the median income has dropped significantly since 2000. The inequalities that have worsened in the US since 1980 have hurt the bottom half significantly.

Here is a summary from USAToday in 2011 (link):

Median household income fell 2.3% to $49,445 last year and has dropped 7% since 2000 after adjusting for inflation, the Census Bureau said Tuesday. Income was the lowest since 1996.

Poverty rose, too. The share of people living in poverty hit 15.1%, the highest level since 1993, and 2.6 million more people moved into poverty, the most since Census began keeping track in 1959.

The poverty statistic is stunning: it implies that 30 percent of the bottom 50 percent are officially living in poverty -- almost one-third.

So how do the bottom half of Americans do when it comes to health insurance? The Kaiser Family Foundation provides a major data source on rates of uninsured adults by income group (link). Here is a data snapshot for uninsured non-elderly Americans by income:

This shows that 58% of non-elderly Americans with income below 250% of the Federal poverty line are uninsured, while 12% of non-elderly Americans between 250% and 400% of FPL are uninsured. Only 5% of non-elderly Americans with income in excess of 400% of the Federal poverty line are uninsured.

What does this distribution of uninsured status across income imply for the bottom half of Americans? This requires some calculation. Here are the Federal poverty lines for 2011 (link):

A household of 4 persons has a Federal poverty line of $22,350 on this standard, so 250% of this is $55,875 -- a bit above the median household income for 2011. So lack of health insurance is heavily concentrated in the bottom 50 percent.

Home foreclosure is another reality in middle income America. Foreclosure has been a reality across full range of the income spectrum since 2008. But it appears to be more devastating in the bottom half of the income distribution. (This is evident in Detroit and Southeast Michigan.)

What is our society doing about these basic realities? Not very much. And, of course, a major candidate for President is on record: "I'm not concerned about the very poor" (link). One would hope that the bottom 50 percent think very carefully about which political platform best serves their real interests, including maintenance of a social safety net, aggressive and effective efforts to stimulate job growth, tax reform that requires the affluent to pay their fair share, and preservation of the broadened health insurance coverage promised by the 2010 health care reform legislation.

(Here is a piece in the New York Times on median income; link.)

Causal realism and historical explanation

2012-04-07T15:07:00.000-04:00

Are there plausible intuitions about the ways the world works that stand as credible alternatives to Hempel's covering law model? There are. A particularly strong alternative links explanation to causation, and goes on to understand causation in terms of the real causal powers of various entities and structures. Rom Harre's work explored this approach earliest (Madden and Harre, Causal Powers: Theory of Natural Necessity), and Roy Bhaskar's theories of critical realism push these intuitions further (Critical Realism: Essential Readings (Critical Realism: Interventions)). Bhaskar and Archer's volume Critical Realism: Essential Readings (Critical Realism: Interventions) (Bhaskar, Archer, Collier, Lawson, and Norrie, eds.) is a good exposure to current controversies in this tradition. Paul Lewis's "Realism, Causality, and the Problem of Social Structure" (link) is worth reading as well.

Here the idea is that causation is not to be understood along Humean lines, as no more than constant conjunction. (This is where the insistence on general laws originates.) Instead, the idea of a causal power is taken as a starting point. Things have the capacity to bring about changes of specific circumstances, in virtue of their inner constitution (or what Harre is content to call their essences). (I would put Nancy Cartwright's ideas about causation and general laws in the same general vicinity (How the Laws of Physics Lie, Nature's Capacities and Their Measurements), though she is not a critical realist. But her critique of laws and her preference for capacities is similar.)

This doesn't mean that there is a bright line between causal powers and regularities. If a certain thing X has the power to bring about Y, then it is true that there is some generalization available along the lines of "whenever X, Y occurs." The point here is about ontological primacy: is it the power or the law that is more fundamental? And Harre, Bhaskar, and Cartwright all agree that it is the power that is basic and the thing's powers are dependent upon its real constitution.

This set of realist intuitions about causation comports very well with the theory of causal mechanisms. According to this approach, when we ask for an explanation of something, we are asking questions along these lines: what are the real embodied mechanisms that bring about a given outcome? And what is the underlying substrate that gives these mechanisms their causal force?

When causal realism is brought to the social and historical sciences, it brings the idea that there are structures, entities, and forces in the social world that really exist and that supervene upon a substrate of activity that give substance to their causal powers. In the case of the social world, that substrate is the socially constituted, socially situated actor, or what I call the premise of methodological localism.

One implication of this ontology is directional for setting a program of inquiry. Instead of looking for general laws of a given domain, the researcher is encouraged to discover the particular causal properties and powers of specific kinds of things.

This emphasis on the particular and the local is particularly well suited to the challenges of historical and social research. Nancy Cartwright doubts the validity of searching for even exact laws of physics. And this doubt is all the more reasonable in the case of social phenomena. It is pointless to look for general laws of bureaucracy, the military, or colonialism. What is more promising, however, is to examine particular configurations of institutions and settings, and to attempt to determine their causal powers in the setting of a group of social actors.

Suppose we are interested in France's collapse in the Franco-Prussian War (link). We might expend significant research work on discerning the organizational and command structure of the French Army in the 1850s and 1860s. We might look in detail at Napoleon III's state apparatus, including its international relations bureau. And we might gather information on the structure, capacity, and organization of the French rail system. Then we might offer an explanation of a numer of events that occurred in 1870 as the result of the causal properties of those historically embodied organizations and institutions. The real performance properties of the rail system under a range of initial conditions can be worked out. The conditions presented by the rapid mobilization required by suddenly looming war can be investigated. And the logistical collapse that ensued can be explained as the result of the specific causal properties of that complex system. And here is an important point: the Italian rail system at the time had some similarities and some differences. So it is a matter of empirical and theoretical investigation to arrive at an account of the causal properties of that system. We cannot simply infer from the French case to the Italian case, and of course we can't hope to find a general law of rail systems.

The point here is a fundamental one. The covering law model depends on a metaphysics that gives primacy to laws of nature. The framework of critical realism and its cousins depends on a view of the world as consisting of things and processes with real causal powers. This intellectual framework is applicable to the social world as well as to the natural world. And it provides a strong intellectual basis for postulating and investigating social causal mechanisms. Any conception of causal powers requires that we have an idea of the nature of the substrate of causation in various areas. And the social metaphysics of actor-centered sociology provide a strong candidate for such a framework in the case of social causation.

Rawls and exploitation

2012-04-03T21:42:00.000-04:00

image: Karl Marx by David Levine

It is interesting to consider whether the principles of justice that Rawls describes in A Theory of Justice would in fact permit economic exploitation in Marx’s sense of the term. Do Rawls's two principles of justice permit what Marx would call systemic exploitation of one group of individuals by another? A very interesting post by Will Wilkinson in BigThink suggests that Rawls was a more radical critic of capitalism than we thought, and the reasoning he puts forward is very relevant to the question of justice and exploitation.

First, the basics. Marx believed that the greatest accomplishment of his economic theory in Capital (link) was its ability to explain how exploitation could occur within a system of free and unforced exchanges among equals, including employers of labor and sellers of labor time. The exploitation of the serf by the lord within feudalism depends on forcible extraction and coercion. But how could exploitation take place in a system of free exchange?

Marx’s concept of exploitation is formulated in the language of labor value and surplus value. The value of a commodity is equal to the quantity of socially necessary labor time involved in its production. The capitalist purchases the worker’s labor time for a wage that is the equivalent of a certain number of labor hours X. The length of the working day is greater than X. The capitalist subtracts the cost of constant capital (machinery depreciation, space, and raw materials), and is left with a positive sum of value in the form of profit. And this fund of surplus value permits accumulation into the next cycle of economic activity. Marx describes this as extraction of surplus value and as technical exploitation by the capitalist of the worker.

The key question about whether exploitation is just by Rawls's principles, then, is whether the two principles permit private ownership of the means of production and whether they permit a generalized system of wage labor in which the labor time of the worker is purchased on the basis of a wage set by a competitive labor market. If so, then Marx would conclude that exploitation is compatible with the principles of justice; if not, then we have a basis for thinking that the two principles are powerful enough to rule out exploitation.

Rawls is explicit in holding that laissez-faire capitalism is unjust. This is because of the difference principle. The difference principle mandates that the condition of the worker should be better than it would be without this system of capital and labor, which may entail transfer of wealth through taxation to bring the worker’s welfare up to that standard. Laissez-faire capitalism is not just, according to the two principles because it lacks fiscal and legislative means for transferring wealth to improve the condition of the least-well-off (see the discussion of a property-owning democracy in an earlier post). But if just institutions permit ownership of capital and generalized wage labor, then Marx would still regard this as a system of exploitation and surplus extraction.

So the key question is whether the two principles of justice permit private property in the means of production and a system of wage labor. There are two plausible approaches we can take on this question, leading to different results.

The answer, it would appear, does not depend on the second principle of justice (the difference principle) but rather the first principle of justice (the liberty principle). This is Wilkerson's central point: does the liberty principle include protection of economic rights, including the right to own the means of production and the right to buy and sell labor power?

It is possible to read the liberty principle as representing a form of Lockean liberalism, with rights of life, liberty, and property to be protected above all else. And in fact, Rawls explicitly includes the right to hold (personal) property as a right protected by the liberty principle. It is only a small step to argue that ownership of property extends to all potential things. On this interpretation, some form of capitalism follows. If the first principle permits private ownership of property, including property in the means of production, then it is not inherently unjust to derive income from ownership of property and to hire workers to make one's property "productive". Further, if the first principle entails the right to use one's labor as one chooses, then presumably one has the right to sell one's labor time. This is the essence of capitalism. The second principle may moderate the effects of this system; but at best we get welfare capitalism instead of laissez-faire capitalism, and we get exploitation in the technical sense. A surplus is transferred from the workers who create it to the owners of capital.

But perhaps the liberty principle doesn't in fact support these economic rights after all. This is Wilkerson's argument, and it is the basis for his claim that Rawls is more radical than we thought. And it is the view that Sam Freeman explores in greater depth in his book Rawls. In a nutshell, Freeman gives an extensive argument for concluding that Rawls does not include these economic rights under the liberty principle (the right to own and accumulate capital and the right to buy and sell labor time). Here is Freeman's position:

Then again, Rawls resembles Mill in holding that freedom of occupation and choice of careers are protected as a basic freedom of the person, but that neither freedom of the person nor any other basic liberty includes other economic rights prized by classical liberals, such as freedom of trade and economic contract. Rawls says that freedom of the person includes having a right to hold and enjoy personal property. He includes here control over one's living space and a right to enjoy it without interference by the State or others. The reason for this right to personal property is that, without control over personal possessions and quiet enjoyment of one's own living space, many of the basic liberties cannot be enjoyed or exercised. (Imagine the effects on your behavior of the high likelihood of unknowing but constant surveillance.) Moreover, having control over personal property is a condition for pursuing most worthwhile ways of life. But the right to personal property does not include a right to its unlimited accumulation. Similarly, Rawls says the first principle does not protect the capitalist freedom to privately own and control the means of production, or conversely the socialist freedom to equally participate in the control of the means of production (TJ, 54 rev.; PL, 338; JF, 114). (Kindle Locations 1239-1248).

Unlike John Locke, then, John Rawls does not accept the fundamental moral rights that give rise to capitalism as basic rights of liberty. If these rights are to be created within a just society, they must be governed by the difference principle. Or in more contemporary terms: Rawls and Nozick part ways on liberties even more fundamentally than they do on distributive justice (Anarchy, State, and Utopia).

If we accept Freeman's argument (and Wilkinson's) -- and I am inclined to -- then the answer to the question posed above is resolved. The two principles of justice are not apriori committed to the justice of the basic institutions of capitalism; and therefore Rawls's system is not forced to judge that exploitation is just. Or more affirmatively: exploitation is unjust.

What is surprising about this conclusion is the fact that it is surprising, now forty years after the original publication of A Theory of Justice. The first generation of readers of the theory formed a compelling impression that the book was largely centered on liberal welfare market society -- perhaps something along the lines of Nordic social democracy. And yet the passages and ideas that Freeman calls out were there all along. So it is surprising that the radicalism of Rawls's critique was not better recognized in the 1970s.

Rawls and classical political economy

2012-04-01T20:38:00.000-04:00

John Rawls's A Theory of Justice is highly relevant to the ways we think about our economic system. If we just read the citations, Rawls seems to be primarily influenced by "modern" economics -- Samuelson, equilibrium theory, game theory, and marginalist theory. And so we might suppose that his moral worldview reflects a neoclassical vision of economy and society. However, his thought actually seems to reflect a recognition of the intellectual tension between classical political economy and “modern economics”. In some ways his framework for thinking about our contemporary economy seems to be closer intellectually to Mill, Ricardo, and Marx than it is to Pareto and Samuelson.

Classical political economy was premised on the labor theory of value—the idea that there is a concrete, economically meaningful measure of value that guides economic organization. Further, there was the idea that the economic needs that individuals had were also concrete—the consumption goods that permitted life to proceed. These goods included items like food, clothing, shelter, medicines, and perhaps schooling. So economic activity, according to the classical economists, was about something objective.

Neoclassical economy, by contrast, rejected even the idea of utility as a concrete or objective human reality. Instead, modern economics bracketed the reality of needs in favor of a metaphysics of subjective preference. Economists no longer needed to think about what people needed, but rather simply what they preferred; so the utilities "consumers" ascribed to outcomes could be discovered by the quasi-experiments of “revealed preference.” Welfare was then defined as the extent to which the individual can satisfy the range of subjective preferences he or she happens to have. So classical and modern economic paradigms differ substantially on what economic activity ought to achieve: satisfaction of material needs, for the classical economists; and satisfaction of subjective preferences, for the modern economists.

A major thrust of the critique of neoclassical economics arises at just this point. Development organizations like the Dag Hammarskjöld Foundation and economists like Amartya Sen have put forward fundamentally different ideas about human wellbeing. The basic needs approach disputed that the goal of economic development in poor countries should be defined in terms of subjective preferences or utilities. These thinkers argued instead for achieving a decent minimum for whole populations in the satisfaction of basic needs. A 1975 report from the Dag Hammarskjöld Foundation to the United Nations (What Now – the 1975 Dag Hammarskjöld Report on Development and International Cooperation; link) is illustrative; it emphasized the idea of basic needs within the discussion of development priorities.

Amartya Sen went a step further, by introducing a more adequate theory of the human person in terms of capabilities and functionings, and argued for a conception of wellbeing that is defined in terms of the ability of individuals and populations to realize their capabilities. Sen advanced these ideas in many places, including On Economic Inequality and Development as Freedom. (Earlier posts have discussed the capabilities approach; link, link.) These are objective criteria of wellbeing, not simply summations of subjective preference satisfaction. And these frameworks of thought present a major challenge to the foundations of modern economic thought.

In light of these observations, it is very interesting to observe that Rawls defined the foundation of his theory of justice, the original position, in terms that are strikingly classical. In the original position, representative individuals are asked to deliberate behind a veil of ignorance about what principles of justice they would choose to regulate their social cooperation and competition. Individuals are presumed to be mutually disinterested, and their sole concern is to adopt principles that they can live with in the resulting society. But what are their interests? Rawls says that the participants in the OP are interested in a set of primary goods: material resources and liberties, essentially. These are "things which a rational man wants whatever else he wants" (TJ:92).

So Rawls's definition of the situation of deliberation within the original position is one that focuses on primary goods, not subjective utilities. And this sounds much closer to a classical assumption about economic interests and the human good than it does a modern assumption. It offers an objective and realistic assumption about what people need in order to live decent lives.

This line of thought is supported by a second feature of Rawls's philosophical orientation. The most basic substantive moral position that Rawls takes is his rejection of utilitarianism as a general principle of justice. Just institutions are not defined as those that "create the greatest good for the greatest number." Instead, they are defined as those that can be assured to provide fair circumstances of life for every citizen. This is established by the unanimity rule. Choice within the original position must be unanimous; and this means that it needs to support the interests of every participant. In order to make the idea of the OP an intelligible one, Rawls needs to specify a decision rule for the participants. He argues for the maximin rule over the expected utility rule: the participants will each choose the path that has the least-bad worst outcome. This choice of decision rule, it should be emphasized, does not reflect an assumption about risk-averse psychology, but rather a compelling reason for choosing this rule. The stakes are too high to do otherwise. So when participants deliberate among institutional alternatives from the perspective of the maximin rule, they will choose a governing norm like the difference principle. And this too seems to be an implicit rejection of the foundations of modern economics, including the theory of subjective utility and the idea that the only thing that matters from a moral point of view is maximizing "welfare". Here Rawls draws on Kant, to recognize that the way that social outcomes arise is morally as important as the value of the outcomes themselves. Rights based on justice can be in tension with overall maximum utility.

So I'm inclined to argue that the greatest contribution Rawls made to contemporary economics is his strong and philosophically convincing case for primary goods and his definition of a good life. His rationale for primary goods is that a person’s ultimate goals are set by his or her conception of the good, and there is no reason to expect there to be a common agreed-upon standard for the conception of the good. It is logical, however, to observe that there are some goods that every individual requires in order to pursue any conception of the good: access to material resources and liberties. This seems like a nod towards the moral worldview of classical political economy.

(See a post on "property-owning democracy" for more discussion of the institutional implications of Rawls's reasoning.)

Hempel after 70 years

2012-03-30T20:25:00.001-04:00

Carl Hempel published his sole contribution to the philosophy of history in 1942, almost exactly 70 years ago. The article is "The Function of General Laws in History" (link), and it set the stage for several fruitless decades of debate within analytic philosophy about the nature of historical explanation. Hempel argued that all scientific explanation has the same logical structure: a deductive (or probabilistic) derivation of the explanandum from one or more general laws and one or more statements of fact. Explanation, in Hempel's view, simply is "derivation of the explanandum from general laws." Here is the opening paragraph of the essay.

It is a rather widely held opinion that history, in contra-distinction to the so-called physical sciences, is concerned with the description of particular events of the past rather than with the search for general laws which might govern those events. As a characterization of the type of problem in which some historians are mainly interested, this view probably can not be denied; as a statement of the theoretical function of general laws in scientific historical research, it is certainly unacceptable. The following considerations are an attempt to substantiate this point by showing in some detail that general laws have quite analogous functions in history and in the natural sciences, that they form an indispensable instrument of historical research, and that they even constitute the common basis of various procedures which are often considered as characteristic of the social in contradistinction to the natural sciences. (35)

And here is the logical structure of such a "covering law" explanation, according to Hempel:

(1) a set of statements asserting the occurrence of certain events C1, . . . C, at certain times and places,
(2) a set of universal hypotheses, such that
(a) the statements of both groups are reasonably well confirmed by empirical evidence,
(b) from the two groups of statements the sentence asserting the occurrence of event E can be logically deduced. (36)

He is emphatic, moreover, in insisting that valid explanations in history must have this form:

We have tried to show that in history no less than in any other branch of empirical inquiry, scientific explanation can be achieved only by means of suitable general hypotheses, or by theories, which are bodies of systematically related hypotheses. (44)

Hempel concedes the point that few existing historical explanations actually look like this, with explicit law statements embedded in a deductive argument; but he argues that this shows only that existing explanations are elliptical, incomplete, or invalid. And often, he finds, what is offered as a historical explanation is in fact no more than an "explanation sketch" (42), with placeholders for the general laws.

What kinds of general laws does Hempel think that historians have in the back of their minds when they offer elliptical explanations? He refers to regularities of individual or social psychology (40), regularities of collective behavior ("groups migrate to regions which offer better living conditions"), or at the macro level, regularities linking growing discontent to the outbreak of revolution (41). Further:

Many of the universal hypotheses underlying historical explanation, for instance, would commonly be classified as psychological, economical, sociological, and partly perhaps as historical laws; in addition, historical research has frequently to resort to general laws established in physics, chemistry, and biology. (47)

This set of assumptions leads to big trouble for historical explanation if we accept Hempel's account, however, because it is hard to think of a real historical research question where there might be a set of social or individual regularities sufficient to deductively entail the outcome. Bluntly, the social and behavioral sciences have never produced theories of individual or collective behavior that issue in statements of general laws that could be the foundation for a covering law explanation. And given that social phenomena are formed by actors with a range of features of agency and decision-making, we have very good reason to think that this lack of regularities is inherent in the social world. The social world is simply not governed by a set of social or individual laws. Let's look at that point at several levels.

Individuals. The social sciences provide a good basis for advancing theories of agency, which in turn support certain generalizations about action. For example: People act out of self interest. People act morally. People pay attention to the example of others. People care about their families and friends. People follow charismatic leaders. People follow the precepts of their religious beliefs. People are emotional and short-sighted. People make decisions based on specific heuristics and rules-of-thumb. Each of these statements takes the form of a generalization. And each is true -- of some delimited groups of agents some of the time. But there is no generalization about agency that is true of all agents all the time. Rational choice theory attempts to provide a single theory of agency and decision making that replaces all of these variant grounds of action. But rational choice theory has proven notoriously unsuccessful as a foundation for explanation of a large and complex event -- war, revolution, economic crisis.

Groups. Here too we can identify some partial regularities: Groups tend to coalesce in action when they have prominent shared characteristics. Groups are more prone to panic than individuals. Groups tend to fail to accomplish collective purposes. Groups are hyper-sensitive to racial and ethnic markers. And so forth. It is evident that these are partial, tendential, exception-laden, and inexact; not at all like the generalizations that characterize metals, liquids, or proteins.

Organizations and institutions. What about mid-level social arrangements like labor unions, congregations, and terrorist cells? It's not that there aren't any generalizations to be had concerning items at this level; it is that there are too many, and they are highly contingent, conditioned, and contradictory. Certain types of organization are more prone to accidents than others. This is true; but we have more confidence in our analysis of the most important features of the high-safety organization than we have in the corresponding generalization. So there isn't a stockpile of laws that might be produced to apply to a social situation and then turn the crank and derive the deductive consequences.

Finally, what about large-scale events and structures -- wars, revolutions, civil conflict? Here too there are some generalizations that social scientists have asserted. For example: Democracies don't go to war with each other. War is made more likely when two powers have conflicts of interest over important resources. Wars create propaganda. Revolutions don't happen when the general population is satisfied. But generalizations about these sorts of social entities too are bounded and unreliable. They are conditional, we recognize immediately that they have exceptions, and they don't permit prediction.

So the strong, governing generalizations that would be needed for a covering law explanation do not exist. As I argued a number of years ago, social regularities are phenomenal, not governing (link); they reflect characteristics of the actors rather than governing the behavior of the ensembles. Does this mean that historical explanation is impossible? No. But we need to turn our attention from regularities to causal mechanisms and powers in order to see what a good historical explanation looks like. A good historical explanation identifies a number of independent mechanisms and processes that are at work in a particular circumstance, and then demonstrates how these mechanisms, and the actions of the actors involved, lead to the outcome.

Doug McAdam, Sidney Tarrow, and Chuck Tilly advanced a boldly different approach to analyzing and explaining complex historical phenomena, with special application to social contention. They rejected the idea that there might be "laws" of revolution, civil unrest, or ethnic cleansing. They argued instead that there are a number of recurring "social mechanisms" of contention that can be identified in many instances of contention, and whose influences can be traced out to result in the observed outcomes. Here is how McAdam, Tarrow and Tilly proceed in Dynamics of Contention.

We begin with a question: What led normally accepting accepting African-Americans both in Montgomery and throughout the South to risk their livelihoods and their lives in support of civil rights? Recall from Chapter I that in the "classical social movement agenda" the following factors come into play:

Social change processes initiate a process of change and trigger changes in the political, cultural, and economic environments.
Political opportunities and constraints confront a given challenger. Though challengers habitually face resource deficits and are excluded from routine decision making, the political environment at any time is not immutable; the political opportunities for a challenger to engage in successful collective action vary over time. These variations shape the ebb and flow of a movement's activity.
Forms of organization (informal as well as formal) offer insurgents sites for initial mobilization at the time opportunities present themselves and condition their capacity to exploit their new resources. Despite some evidence to the contrary (Piven and Cloward 1977), a large body of evidence finds organizational strength correlated with challengers' ability to gain access and win concessions (Gamson 1990).
Framing, a collective process of interpretation, attribution, and social construction, mediates between opportunity and action. At a minimum, people must both feel aggrieved at some aspect of their lives and optimistic that acting collectively can redress the problem (Snow, et al. 1986; Snow and Benford 1988). Movements frame specific grievances within general collective action frames which dignify claims, connect them to others, and help to produce a collective identity among claimants.
Repertoires of contention offer the means by which people engage in contentious collective action. These forms are not neutral, continuous, or universally accessible; they constitute a resource that actors can use on behalf of their claims (Traugott, et al. 1995). The use of transgressive forms offers the advantages of surprise, uncertainty, and novelty, but contained forms of contention have the advantage of being accepted, familiar, and relatively easy to employ by claimants without special resources or willingness to incur costs and take great risks.

That classical agenda made three enduring contributions to the study of social movements. First, it made strong claims regarding the close connection between routine and contentious politics, helping to reframe the study of social movements as the proper province of both sociology and political science. Second, calling attention to the role of "mobilizing structures," it represented a powerful challenge to the stress on social disorganization and breakdown in the older collective behavior paradigm. Third, it produced a credible picture of mobilization into social movements that was supported by a good deal of empirical evidence correlating the factors outlined above with increases in mobilization.

There are low-level generalizations offered throughout this series of statements. But all those generalizations are soft and exception-laden. What MTT are interested in doing when they attempt to explain what they call "episodes of contention" is rather to identify the occurrence and interaction of a number of common mechanisms of contention. And in fact, they explicitly repudiate the covering law model:

Our emphasis on recurring mechanisms and processes does not mean that we intend to pour all forms of contention into the same great mold, subjecting them to universal laws of contention and flattening them into a single two-dimensional caricature. On the contrary, we examine partial parallels in order to find widely operating explanatory mechanisms that combine differently and therefore produce different outcomes in one setting or another. To discover that third parties influence both strikes and ethnic mobilization by no means amounts to showing that the origins, trajectories, and outcomes of strikes and ethnic mobilization are the same, any more than identifying similarities in memory processes of mice and men proves mice and men to be identical in all regards. To discover mechanisms of competition and radicalization in both the French Revolution and in the South African freedom movement is not to say that the Jacobins and the African National Congress are the same. We pursue partial parallels in search of mechanisms that drive contention in different directions. Only then, and in Part III, do we examine how mechanisms combine in robust political processes.

Seventy years after Hempel's classic article, the covering law theory is now generally regarded as a fundamentally wrong-headed way of thinking about historical (and social) explanation. Logical positivism is not a convenient lens through which to examine the social and historical sciences. There is too much contingency in the social world. Rather than being the result of law-governed processes, social outcomes proceed from the contingent and historically variable features of the actors who make them. So the attention of many people interested in specifying the nature of historical and social explanation has focused on social mechanisms constituted and driven by common features of agency.

(Renate Mayntz's discussion of causal mechanisms represents one of the best current treatments of the subject; link.)

Culture or jobs?

2012-03-28T18:11:00.000-04:00

Stephen Steinberg contributed a provocative but important piece to Boston Review a year ago on current academic thinking about race and poverty. The piece is titled Poor Reason: Culture Still Doesn't Explain Poverty, and it is now available as a short Kindle publication. The topic Steinberg focuses on is deeply important -- fundamentally, how to explain and remediate the persistent fact of poverty in the African American population in the United States. And anyone who is paying attention to urban America knows that the economic and social situation of much of the African-American population of the United States is bad, and in many respects barely improved over the past 40 years.

Putting the point most bluntly: is the primary explanation of persistent urban African American poverty the cumulative workings of a set of racially discriminatory economic and social structures? Or is it some set of factors that have been internalized within African American culture and values, persisting long after discrimination has disappeared?

Steinberg's polemic is a response to a special 2010 issue of Annals of the American Academy of Political and Social Science on "new" approaches to the role of culture in poverty in a racialized America. The old approach was stimulated by Daniel Patrick Moynihan's assertions about the black family offered in The Negro Family: The Case for National Action in 1965. Moynihan's position paper for the Johnson administration provoked a firestorm of criticism when it was leaked, and some observers believe that the ensuing divisiveness, between progressives and conservatives and within the progressive movement itself, contributed to the failure of the Johnson administration to seriously address the structural issues of race that our country faced then (and now). One version of the view attributed to Moynihan is that it is difficulties with the African American family that are the root cause of persistent African American poverty. This is the "culture" end of the story. (I'll note below that most of the contributors do not agree with this reading of Moynihan.) The "jobs" end is the view that the key issue of racial disadvantage in American society was (and is) the lack of economic opportunities and jobs for many millions of young African Americans, and that cultural and family characteristics are shaped by this basic fact.

Steinberg takes a very sharp stand against the "culture" stream of research on the question of persistent African American poverty:

These myths add up to something -- a perverse obfuscation of American racial history.

Instead, he believes our attention needs to be directed to the structural disadvantages created for African Americans within our economic and social system:

Or do we have to transform the ghetto itself, not by reconstructing the identities of its people, but through a wholesale commitment to eliminating poverty and joblessness?

And he maintains that the "culture" myth originated with Moynihan's report in 1965:

Moynihan made the fatal error of inverting cause and effect. Although he acknowledged that past racism and unemployment undermined black families, he held that the pathology in "the Negro American family" had not only assumed a life of its own, but was also the primary determinant.

Steinberg's central conviction here and elsewhere in other writings is surely correct: the root cause is the political economy of race and the persistent limitation of economic opportunities for African Americans. American society continues to present very high obstacles to African American young people when it comes to gaining admission to the job system, including residential segregation and chronically poor schooling. And as a society and a generation of commentators, we don't pay nearly enough attention to these facts about the political economy of race in America. In particular, Steinberg faults the sociologists and ethnographers included in the 2010 Annals collection for this reason:

Aren't we asking the wrong questions? Do the answers bring us any closer to understanding why this nation has millions of racial outcasts who are consigned to a social death?

Against this background, the ballyhooed "restoration" of culture to poverty discourse can only be one thing: an evasion of the persistent racial and economic inequalities that are a blot on American democracy.

So Steinberg harshly faults anyone, including especially conservative commentators, who put the primary causal role on culture. But Steinberg also attributes this blindness about the structural causes of racial inequality and poverty to the current poverty and race research community as represented by this Annals collection, and I'm not persuaded this is justified.

In fact, it doesn't seem to be true to say that Moynihan himself disagreed with Steinberg about which factor is most important. Rather, Moynihan described the problems with the African American family that he identified as endogenous -- caused by the facts of racial discrimination and economic disadvantage -- rather than exogenous -- an independent cause of poverty. The original cause, persisting into the present, is the structural circumstance of high unemployment and limited economic opportunities for African American young people.

The 2010 Annals volume was followed by a second collection in 2012, edited by Douglas Massey. Massey's volume, The Moynihan Report Revisited: Lessons and Reflections after Four Decades (link), is also focused on the Moynihan report and is a contribution of at least equal importance. This collection too focuses on the contrast between culture and structures as explanations of persistent poverty. But unlike the 2010 collection, this collection gives greater attention to structural factors that appear to be at work.

Massey and Robert Sampson point out in their introduction to the 2012 volume that Moynihan's original argument invoked both family and jobs; and in fact, Moynihan got the arrow of causation going in the same direction as Steinberg wants it to go. They claim that Moynihan's argument was that it was necessary to break the cycle of poverty by creating abundant opportunities for jobs for young African American men. The logical implication of his argument was establishment of a massive Federal jobs program to break the logjam of African American unemployment. Massey and Sampson paraphrase his theory: "If full employment for black males—especially young black males—could be achieved, he thought, then family stability could be restored and government would be in a better position to attack more entrenched problems such as discrimination and segregation."

The 2012 volume focuses on more of the structural causes at a range of levels of African American poverty and reduced opportunity. Harry Holzer reviews current research on the ways in which young African-American men are incorporated (or not) into the labor market. Devah Pager and Diana Karafin examine the workings of discrimination and stereotypes in employer decisions about hiring. Andrew Cherlin et al attempt to assess the effects of welfare reform on African American and Hispanic families in the 2000s. In "Racial Stratification and the Durable Tangle of Neighborhood Inequality" Robert Sampson reviews empirical work on the ways in which residential neighborhoods influence behavior and outcomes. Sampson finds that Moynihan offers some ideas that are very consistent with current thinking about the "ecological" influences on poverty and the characteristics of poverty in an urban location. Almost all these authors give credit to Moynihan for accurately perceiving the reality of racial inequality and African American poverty in the 1960s, and they confirm that Moynihan emphasized the primacy of jobs as an instigating cause of these outcomes.

So it seems that the current wave of social science research on race and poverty is doing a much better job of addressing the causal factors involved than Steinberg allows. To me, anyway, it seems that Steinberg's critique confuses two things: the urgency of addressing structural racism (yes!) and the value of attempting to better understand the cultural systems through which poor communities navigate their lives (also yes!). Steinberg puts it forward that we need to choose one to the exclusion of the other; but that is unconvincing to me. When Al Young offers an empirical and theoretical account of the role of "framing" in the choices made by poor people in the 2010 volume, he is adding something of real value to our understanding of the workings of economy, culture, and race within the circumstances of urban poverty. This understanding can then be deployed in the design of a variety of policy efforts, including programs aimed at improving the health status of young African American men. But Steinberg dismisses this work:

Enter the sociologist, to record the agony of the dispossessed. Does it really matter how they define a "good job" when they have virtually no prospect of finding one?

Rhetoric aside, I'd say that the analysis of the experience of poverty and the repertoires employed to survive in that environment is indeed important; it really does matter.

In short, it seems to me that Steinberg's criticisms are properly addressed to conservative commentators on African American poverty who do indeed blame the victim; but that virtually none of the scholars included in either of these Annals volumes are guilty of this injustice.

(Steinberg spells out more of his critique in Turning Back: The Retreat from Racial Justice in American Thought and Policy.)

Philosophy and social knowledge

2012-03-24T16:38:00.000-04:00

Throughout this blog I’ve addressed a very large subject: what is involved in understanding society? What sorts of ontological assumptions do we need to make as we attempt to analyze and explain social processes? What is involved in explaining some of the social outcomes we are most interested in? How do we provide empirical confirmation for our hypotheses and theories about the social world? What help or hindrance can be derived from the legacies of positivism and naturalism? Finally, how can philosophy contribute to the creation of a better approach to the social sciences for the twenty-first century?

The philosophy of social science is a group of research traditions that are intended to shed light on various aspects of the intellectual effort of understanding and explaining social phenomena. In brief, it is the study of the social sciences from the point of view of the quality of knowledge they offer, the types of explanations they advance, and the important conceptual problems that are raised in the course of social science research. Core questions include: What are the scope and limits of scientific knowledge of society? What is involved in arriving at a scientific understanding of society? What are the most appropriate standards for judging proposed social explanations? Is there such a thing as social causation? How are social theories and assertions to be empirically tested? How do social facts relate to facts about individuals?

The philosophy of social science is in one sense a “meta” discipline—it reviews and analyzes the research of other, more empirical researchers. But in another sense the philosopher is a direct contributor to social science research; by discussing and reflecting upon the methods, assumptions, concepts, and theories of working social scientists, the philosopher is also contributing to the improvement of social science research. On this perspective it is arbitrary to draw a line between the theoretical and conceptual inquiry of the applied social scientist, and the similar studies of the philosopher.

A philosophy can guide us as we construct a field of knowledge, and it can serve as a set of regulative standards as we conduct and extend that field of knowledge. Philosophy has served both intellectual functions for the social sciences in the past century and a half. Philosophical ideas about the nature of knowledge and the nature of the social world guided or influenced the founding efforts by such early social researchers as Weber, Durkheim, or Spencer in the formulation of their highest-level assumptions about social processes and their most general assumptions about what a scientific treatment of society ought to look like. So there has been an important back-and-forth between philosophy and the social sciences from the start. John Stuart Mill and William Whewell framed many of the assumptions about the social sciences that would govern the development of many areas of the social sciences in the English-speaking world; whereas European philosophers such as Heinrich Rickert and Wilhelm Dilthey articulated a vision of the “human sciences” based on the idea of meaningful action that would have great influence on European social science development. At its best, philosophy can function as an equal collaborator with the creators and practitioners of the social sciences, helping to arrive at more durable and insightful theories and methods. At its worst, philosophical doctrines can blind social researchers to more fertile and innovative avenues of theory and explanation.

The importance of the philosophy of social science derives from two things: first, the urgency and complexity of the challenges posed by the poorly understood social processes that surround us in twenty-first century society, and second, the unsettled status of our current understanding of the logic of social science knowledge and explanation. We need the best possible research and explanation to be conducted in the social sciences, and current social science inquiry falls short. We need a better-grounded understanding of the social, political, and behavioral phenomena that make up the modern social world. Moreover, the goals and primary characteristics of a successful social science are still only partially understood. What do we want from the social sciences? And how can we best achieve these cognitive and practical goals? There are large and unresolved philosophical questions about the logic of social science knowledge and theory on the basis of which to arrive at that understanding. And philosophy can help articulate better answers to these questions. So philosophy can play an important role in the development of the next generation of social science disciplines.

It is important to underline the point that this inquiry is not of merely academic concern. Understanding society better is an urgent need for all of us in the twenty-first century. Our quality of life, our physical security, our ability to provide for greater social justice globally and locally, and our ability to achieve the sustainability of our natural environment all depend upon social processes and social behavior. The better we understand these processes and behavior, the better we will be able to shape our futures in ways that serve our needs and values. And currently our understanding of important social processes is highly limited. We need better theories, better research methodologies, and better conceptions of the basis nature of social phenomena, if we are to arrive at a more realistic understanding of the social world. The philosophy of social science can contribute to these important tasks.

Several particularly central ideas emerge from large threads of thought provided here. First is a point about social ontology. Social research should be based on a realistic understanding of the fact that social phenomena are constituted by socially embedded individuals in interaction with each other. Higher-level social entities—states, organizations, institutions—are real enough, but they must be understood as being composed of individuals in interaction. So social science must avoid the error of reification—the assumption that social entities have some kind of abiding permanence independent of the individuals who constitute them. This is the approach I describe as “methodological localism.”

This ontology should in turn lead social researchers to expect a substantial degree of contingency and plasticity in the phenomena they study. Given that institutions and organizations are constituted by the social individuals who make them up, we should expect that they will mutate over time—that is, we should expect plasticity of social entities. And we should anticipate contingency. Rather than the iron laws of history that Marx hoped to find, we should not define “science” as the discovery of law-governed regularities among a set of phenomena.

Finally, it is affirmed here that there is a credible basis for finding a degree of order among social phenomena, in the form of causal relationships between various social facts. The discovery of social causal mechanisms is the foundation of social explanation. Moreover, there is a very consistent relationship between the idea of a social causal mechanism and the social ontology of “socially-situated individuals” that is offered here. Social causation flows through the structured social actions of individuals. And empirical social research can inform us about various aspects of the processes of social causation: the social institutions within which individuals act; the historical processes of development through which individuals came to have their current mental models, moral ideas, and preferences; and the powers and constraints that are embodied in a set of social relationships at a given time.

A recurring theme throughout the blog is attention to the nature of “social causal mechanisms.” The causal mechanisms approach is the most promising way of addressing the idea of explanatory relations among social circumstances, in my view. So it is worthwhile looking carefully at the ways in which social scientists have sought to explain the social outcomes and processes that most interest them and the kinds of causal mechanisms they have identified in a broad range of areas of research.

Another recurring thread in the past several years of the blog is concerned with the mental frameworks within which we attempt to make sense of the social world. This has to do with conceptual frameworks, definitions, theories, and presuppositions. Both ordinary actors and social scientists bring organizing concepts and beliefs to their representations of the social worlds they encounter, and those frameworks themselves are not directly open to empirical examination.

A final perspective found frequently in this blog that seems particularly important for philosophers to acknowledge is a point about methodological pluralism. Sociologists, political scientists, anthropologists, geographers, and public health specialists make use of a very wide range of methods of inquiry, explanation, and justification. And it is often clear that the choices made by a particular investigator or tradition are in fact well adapted to the particular circumstances of the field of research he/she is confronting. So philosophers need to be wary of philosophical positions that seem to imply the need for a single unified theory, method, or system of justification. Rather, the diversity of the social world requires a comparable range of research approaches and theories.

Here is a short video in which Michael Sandel offers his views of the relations that ought to exist between philosophy and the social sciences, especially economics.

Amartya Sen's commitments

2012-03-21T11:50:00.000-04:00

A recent post examined the Akerlof and Kranton formalization of identity within a rational choice framework. It is worth considering how this approach compares with Amartya Sen's arguments about "commitments" in "Rational Fools" (link).

Sen's essay is a critique of the theory of narrow economic rationality to the extent that it is thought to realistically describe real human deliberative decision-making. He chooses Edgeworth as a clear expositor of the narrow theory: "the first principle of Economics is that every agent is actuated only by self interest" (Sen 317, quoting Mathematical Psychics). Sen notes that real choices don't reflect the maximizing logic associated with rational choice theory: "Choice may reflect a compromise among a variety of considerations of which personal welfare may be just one" (324). Here he argues for the importance of "commitments" in our deliberations about reasons for action. Acting on the basis of commitment is choosing to do something that leads to an outcome that we don't subjectively prefer; it is acting in a way that reflects the fact that our actions are not solely driven by egoistic choice. "Commitments" are other-regarding considerations that come into the choices that individuals make.

Sen distinguishes between sympathy and commitment:

The former corresponds to the case in which the concern for others directly affects one's own welfare. If the knowledge of torture of others makes you sick, it is a case of sympathy; if it does not make you feel personally worse off, but you think it is wrong and you are ready to do something to stop it, it is a case of commitment. (326)

The characteristic of commitment with which I am most concerned here is the fact that it drives a wedge between personal choice and personal welfare, and much of traditional economic theory relies on the identity of the two. (329)

Sen thinks that John Harsanyi made an advance on the narrow conception of rationality by introducing discussion of two separate preference orderings that are motivational for real decision-makers: ethical preferences and subjective preferences. (This is in "Cardinal Welfare, Individualistic Ethics, and Interpersonal Comparisons of Utility".) But Sen rightly points out that this construction doesn't give us a basis for choosing when the two orderings dictate incompatible choices. Sen attempts to formalize the idea of a commitment as a second-order preference ordering: a ranking of rankings. "We need to consider rankings of preference rankings to express our moral judgments" (337).

Can one preference ordering do all these things? A person thus described may be "rational" in the limited sense of revealing no inconsistencies in his choice behavior, but if he has no use for these distinctions between quite different concepts, he must be a bit of a fool. The purely economic man is indeed close to being a social moron. Economic theory has been much preoccupied with this rational fool decked in the glory of his one all-purpose preference ordering. To make room for the different concepts related to his behavior we need a more elaborate structure. (335-336)

Here is an example. "I wish I liked vegetarian foods more" is an example of a second-order preference ranking: it indicates a rational preference for the first-order ranking in which the vegetarian option comes ahead of the lamb option over the ranking in which these options are reversed. And Sen's point is an important one: the second-order ranking can be behaviorally influential. I may choose the vegetarian option, not because I prefer it, but because I prefer the world arrangement in which I go for the vegetarian option. Or in other words, one's principles or commitments may trump one's first-order preferences.

Significantly, Sen's thinking on this subject was developed in part through a conference organized by Stephen Körner on practical reason in the 1970s (Practical Reason: Papers and Discussions). This is significant because it focuses attention on a very basic fact: we don't yet have good theories of how a variety of considerations -- ethical principles, personal identities, feelings of solidarity, reasoning about fairness, and self-interest -- get aggregated into decisions in particular choice circumstances.

Other economists might object to this formulation on the basis of the fact that second-order preference rankings are more difficult to model; so we don't get clean, simple mathematical representations of behavior if we introduce this complication. Sen acknowledges this point:

Admitting behavior based on commitment would, of course have far- reaching consequences on the nature of many economic models. I have tried to show why this change is necessary and why the consequences may well be serious. Many issues remain unresolved, including the empirical importance of commitment as a part of behavior, which would vary, as I have argued, from field to field. I have also indicated why the empirical evidence for this cannot be sought in the mere observation of actual choices, and must involve other sources of information, including introspection and discussion. (341-342)

But his reply is convincing. There are substantial parts of ordinary human activity that don't make sense if we think of rationality as egoistic maximization of utility. Collective action, group mobilization, religious sacrifice, telling the truth, and working to the fullest extent of one's capabilities are all examples of activity where narrow egoistic rationality would dictate different choices than those ordinary individuals are observed to make. And yet ordinary individuals are not irrational when they behave this way. Rather, they are reflective and deliberative, and they have reasons for their actions. So the theory of rationality needs to have a way of representing this non-egoistic reasonableness. This isn't the only way that moral and normative commitments can be incorporated into a theory of rational deliberation; but it is one substantive attempt to do so, and is more satisfactory (for me, anyway) than the construction offered by Akerlof and Kranton.

(I also like the neo-Kantian approach taken by Tom Nagel in The Possibility of Altruism as an effort to demonstrate that non-egoistic reasoning is rational.)