In this Part 1, first, we look at the tail of an asset return distribution and compress our knowledge on Value-at-Risk (VaR) to extract the essence required to understand why VaR-stuff is not the best card in our deck. Next, we move to a classical Bayes’ theorem which helps us to derive a conditional probability of a rare event given… yep, another event that (hypothetically) will take place. Eventually, in Part 2, we will hit the bull between its eyes with an advanced concept taken from the Bayesian approach to statistics and map, in real-time, for any return-series its loss probabilities. Again, the probabilities, not certainties.

Both CDS and out-of-money put option can protect investors against downside risk, so they are related while not being mutually replaceable. This study provides a straightforward linkage between corporate CDS and equity option by inferring stock volatility from CDS spread and, thus, enables a direct analogy with the implied volatility from option price. I find CDS inferred volatility (CIV) and option implied volatility (OIV) are complementary, both containing some information that is not captured by the other. CIV dominates OIV in forecasting stock future realized volatility. Moreover, a trading strategy based on the CIV-OIV mean reverting spreads generates significant risk-adjusted return. These findings complement existing empirical evidence on cross-market analysis.

In the current literature, the analytical tractability of discrete time option pricing models is guaranteed only for rather specific types of models and pricing kernels. We propose a very general and fully analytical option pricing framework, encompassing a wide class of discrete time models featuring multiple-component structure in both volatility and leverage, and a flexible pricing kernel with multiple risk premia. Although the proposed framework is general enough to include either GARCH-type volatility, Realized Volatility or a combination of the two, in this paper we focus on realized volatility option pricing models by extending the Heterogeneous Autoregressive Gamma (HARG) model of Corsi et al. (2012) to incorporate heterogeneous leverage structures with multiple components, while preserving closed-form solutions for option prices. Applying our analytically tractable asymmetric HARG model to a large sample of S&P 500 index options, we demonstrate its superior ability to price out-of-the-money options compared to existing benchmarks.

Volatility clustering, long-range dependence, and non-Gaussian scaling are stylized facts of financial assets dynamics. They are ignored in the Black & Scholes framework, but have a relevant impact on the pricing of options written on financial assets. Using a recent model for market dynamics which adequately captures the above stylized facts, we derive closed form equations for option pricing, obtaining the Black & Scholes as a special case. By applying our pricing equations to a major equity index option dataset, we show that inclusion of stylized features in financial modeling moves derivative prices about 30% closer to the market values without the need of calibrating models parameters on available derivative prices.

We analyze the high-frequency dynamics of S&P 500 equity-index option prices by constructing an assortment of implied volatility measures. This allows us to infer the underlying fine structure behind the innovations in the latent state variables driving the evolution of the volatility surface. In particular, we focus attention on implied volatilities covering a wide range of moneyness (strike/underlying stock price), which load differentially on the different latent state variables. We conduct a similar analysis for high-frequency observations on the VIX volatility index as well as on futures written on it. We find that the innovations over small time scales in the risk-neutral intensity of the negative jumps in the S&P 500 index, which is the dominant component of the short-maturity out-of-the-money put implied volatility dynamics, are best described via non-Gaussian shocks, i.e., jumps. On the other hand, the innovations over small time scales of the diffusive volatility, which is the dominant component in the short-maturity at-the-money option implied volatility dynamics, are best modeled as Gaussian with occasional jumps.

The paper proposes a general asymmetric multifactor Wishart stochastic volatility (AMWSV) diffusion process which accommodates leverage, feedback effects and multifactor for the covariance process. The paper gives the closed-form solution for the conditional and unconditional Laplace transform of the AMWSV models. The paper also suggests estimating the AMWSV model by the generalized method of moments using information not only of stock prices but also of realized volatilities and co-volatilities. The empirical results for the bivariate data of the NASDAQ 100 and S&P 500 indices show that the general AMWSV model is preferred among several nested models.

We introduce a tractable class of multi-factor price processes with regime-switching stochastic volatility and jumps, which flexibly adapt to changing market conditions and permit fast option pricing. A small set of structural parameters, whose dimension is invariant to the number of factors, fully specifies the joint dynamics of the underlying asset and options implied volatility surface. We develop a novel particle filter for efficiently extracting the latent state from joint S&P 500 returns and options data. The model outperforms standard benchmarks in- and out-of-sample, and remains robust even in the wake of seemingly large discontinuities such as the recent financial crisis.

Assume that St is a stock price process and Bt is a bond price process with a constant continuously compounded risk-free interest rate, where both are defined on an appropriate probability space P. Let yt=log(St/St−1). yt can be generally decomposed into a conditional mean plus a noise with volatility components, but the discounted St is not a martingale under P. Under a general framework, we obtain a risk-neutralized measure Q under which the discounted St is a martingale in this paper. Using this measure, we show how to derive the risk neutralized price for the derivatives. Special examples, such as NGARCH, EGARCH and GJR pricing models, are given. Simulation study reveals that these pricing models can capture the “volatility skew” of implied volatilities in the European option. A small application highlights the importance of our model-based pricing procedure.

Using the Chinese stock market data from 1997 to 2013, this paper examines the “Sell in May and Go Away” puzzle first identified by Bouman and Jacobsen (2002). We find strong existence of the Sell in May effect, robust to different regression assumptions, industries, and after controlling for the January or February effect. However, part of the puzzle is subsumed by the seasonal affective disorder effect. We then construct a trading strategy based on this puzzle, and find that it outperforms the buy-and-hold strategy and could resist the market downside risk during large recession periods.

In this paper, we propose a trend factor to capture cross-section stock price trends. In contrast to the popular momentum factor constructed by sorting stocks based on a single criterion of past year performance, we form our trend factor with a cross-section regression approach that makes use of multiple trend indicators containing daily, weekly, monthly and yearly information. We find that the average return on the trend factor is 1.61% per month, more than twice of the momentum factor. The Sharpe ratio is more than twice too. Moreover, during the recent financial crisis, the trend factor earns 1.65% per month while the momentum factor loses 1.33% per month. The trend factor return is robust to a variety of control variables including size, prior month return, book-to-market, idiosyncratic volatility, liquidity, etc., and is greater under greater information uncertainty. In addition, the trend factor explains well the cross-section decile portfolio returns sorted by short-term reversal, momentum, and long-term reversal as well as various price ratios (e.g. E/P), and performs much better than the momentum factor.

We propose a new definition of skill as a general cognitive ability to either pick stocks or time the market at different times. We find evidence for stock picking in booms and for market timing in recessions. Moreover, the same fund managers that pick stocks well in expansions also time the market well in recessions. These fund managers significantly outperform other funds and passive benchmarks. Our results suggest a new measure of managerial ability that gives more weight to a fund’s market timing in recessions and to a fund’s stock picking in booms. The measure displays far more persistence than either market timing or stock picking alone and can predict fund performance.

We propose a model of portfolio selection that adjusts an investors’ portfolio allocation in accordance with changing market liquidity environments and market conditions. We found that market liquidity provides a useful “leading indicator” in dynamic asset allocation. Specifically, market liquidity risk premium cycles anticipate economic and market cycles. Investors can therefore act to avoid markets with low liquidity premiums, waiting to extract liquidity risk premiums when the likelihood of extracting a liquidity premium improves. The result, meaningfully enhanced portfolio performance through economic and market cycles, and is robust to transactions costs and alternate specifications.

We propose that fund performance can be predicted by its R2, obtained from a regression of its returns on a multifactor benchmark model. Lower R2 indicates greater selectivity, and it significantly predicts better performance. Stock funds sorted into lowest-quintile lagged R2 and highest-quintile lagged alpha produce significant annual alpha of 3.8%. Across funds, R2 is positively associated with fund size and negatively associated with its expenses and manager's tenure.

Since Lehman Brothers collapsed in 2008, tail-risk hedging has become an increasingly important concern for investors. Traditional approaches, such as purchasing options or variance swaps as insurance, are often expensive, illiquid, and result in a substantial drag on performance. A more prudent, cost-effective way to maintain a constant risk exposure is to actively manage portfolio exposure according to the prevailing volatility level within underlying assets. The authors implement a robust methodology based on Dybvig’s payoff distribution model to target a constant level of volatility and normalize monthly returns. This approach to portfolio and risk management can help investors obtain their desired risk exposures over both short and longer time frames, reduce exposure to tail risk, and in general increase portfolios’ risk-adjusted performance.

Portfolio optimization problems involving value at risk (VaR) are often computationally intractable and require complete information about the return distribution of the portfolio constituents, which is rarely available in practice. These difficulties are compounded when the portfolio contains derivatives. We develop two tractable conservative approximations for the VaR of a derivative portfolio by evaluating the worst-case VaR over all return distributions of the derivative underliers with given first- and second-order moments. The derivative returns are modelled as convex piecewise linear or—by using a delta–gamma approximation—as (possibly nonconvex) quadratic functions of the returns of the derivative underliers. These models lead to new worst-case polyhedral VaR (WPVaR) and worst-case quadratic VaR (WQVaR) approximations, respectively. WPVaR serves as a VaR approximation for portfolios containing long positions in European options expiring at the end of the investment horizon, whereas WQVaR is suitable for portfolios containing long and/or short positions in European and/or exotic options expiring beyond the investment horizon. We prove that—unlike VaR that may discourage diversification—WPVaR and WQVaR are in fact coherent risk measures. We also reveal connections to robust portfolio optimization.

A common challenge in portfolio risk analysis is that certain assets have shorter return histories than others. Unfortunately, many standard portfolio risk analysis techniques—including historical tail risk measurement, regime-dependent risk analysis, and bootstrapping simulations—require full return histories for all assets or risk factors. The author presents easy instructions on how to efficiently combine data for investments whose histories differ in length and offers a new model to better account for non-normal distributions.

Going beyond the simple bid–ask spread overlay for a particular Value at Risk, the author introduces an innovative framework that integrates liquidity risk, funding risk, and market risk. He overlaid a whole distribution of liquidity uncertainty on future market risk scenarios and allowed the liquidity uncertainty to vary from one scenario to another, depending on the liquidation or funding policy implemented. The result is one easy-to-interpret, easy-to-implement formula for the total liquidity-plus-market-risk profit and loss distribution.

This paper proposes a framework for the modeling, inference and forecasting of volatility in the presence of level shifts of unknown timing, magnitude and frequency. First, we consider a stochastic volatility model comprising both a level shift and a short-memory component, with the former modeled as a compound binomial process and the latter as an AR(1). Next, we adopt a Bayesian approach for inference and develop algorithms to obtain posterior distributions of the parameters and the two latent components. Then, we apply the model to daily S&P 500 and NASDAQ returns over the period 1980.1–2010.12. The results show that although the occurrence of a level shift is rare, about once every two years, this component clearly contributes most to the variation in the volatility. The half-life of a typical shock from the AR(1) component is short, on average between 9 and 15 days. Interestingly, isolating the level shift component from the overall volatility reveals a stronger relationship between volatility and business cycle movements. Although the paper focuses on daily index returns, the methods developed can potentially be used to study the low frequency variation in realized volatility or the volatility of other financial or macroeconomic variables.

We test the performance of different volatility estimators that have recently been proposed in the literature and have been designed to deal with problems arising when ultra high-frequency data are employed: microstructure noise and price discontinuities. Our goal is to provide an extensive simulation analysis for different levels of noise and frequency of jumps to compare the performance of the proposed volatility estimators. We conclude that the maximum likelihood estimator filter (MLE-F), a two-step parametric volatility estimator proposed by Cartea and Karyampas (2011a; The relationship between the volatility returns and the number of jumps in financial markets, SSRN eLibrary, Working Paper Series, SSRN), outperforms most of the well-known high-frequency volatility estimators when different assumptions about the path properties of stock dynamics are used.

This paper proposes a simple model for incorporating wrong-way and right-way risk into CVA (credit value adjustment) calculations. These are the calculations, involving Monte Carlo simulation, made by a dealer to determine the reduction in the value of its derivatives portfolio because of the possibility of a counterparty default. The model assumes a relationship between the hazard rate of the counterparty and variables whose values can be generated as part of the Monte Carlo simulation. Numerical results for portfolios of 25 instruments dependent on five underlying market variables are presented. The paper finds that wrong-way and right-way risk have a significant effect on the Greek letters of CVA as well as on CVA itself. It also finds that the percentage effect depends on the collateral arrangements.

We review the theories on how liquidity affects the required returns of capital assets and the empirical studies that test these theories. The theory predicts that both the level of liquidity and liquidity risk are priced, and empirical studies find the effects of liquidity on asset prices to be statistically significant and economically important, controlling for traditional risk measures and asset characteristics. Liquidity-based asset pricing empirically helps explain (1) the cross-section of stock returns, (2) how a reduction in stock liquidity result in a reduction in stock prices and an increase in expected stock returns, (3) the yield differential between on- and off-the-run Treasuries, (4) the yield spreads on corporate bonds, (5) the returns on hedge funds, (6) the valuation of closed-end funds, and (7) the low price of certain hard-to-trade securities relative to more liquid counterparts with identical cash flows,  such as restricted stocks or illiquid derivatives. Liquidity can thus play a role in resolving a number of asset pricing puzzles such as the small-firm effect, the equity premium puzzle, and the risk-free rate puzzle

We propose a new method for measuring the quality of banks' credit portfolios. This method makes use of information embedded in bank share prices by exploiting differences in their sensitivity to credit default swap spreads of borrowers of varying quality. The method allows us to derive a credit risk indicator (CRI). This indicator represents the perceived share of high-risk exposures in a bank's portfolio and can be used as a risk weight for computing regulatory capital requirements. We estimate CRIs for the 150 largest U.S. bank holding companies. We find that their CRIs are able to forecast bank failures and share price performances during the crisis of 2007–2009, even after controlling for a variety of traditional asset quality and general risk proxies.

We investigate a new non-stationary non-parametric volatility model, in which the conditional variance of time series is modelled as a non-parametric function of an integrated or near-integrated covariate. Importantly, the model can generate the long memory property in volatility and allow the unconditional variance of time series to be time-varying. These properties cannot be derived from most existing non-parametric or semi-parametric volatility models. We show that the kernel estimate of the model is consistent and its asymptotic distribution is mixed normal. For an empirical application of the model, we study the daily S&P 500 index return volatility using the VIX index as the covariate. It is shown that our model performs reasonably well both in within-sample and out-of-sample forecasts.

These facts contribute a great deal to understanding but hardly anything to practical play.¹

While traditional histories of mathematical probability start with Pierre Fermat, Pascal and Huygens because they give what are from the modern point of view correct frequentist solutions to the problems of division and expectations in games of chance …the foundations of Huygens’s method (…) was not chance (frequentist probability), but rather sors (expectation) in so far as it was involved in implicit contracts and the just treatment of partners.⁴

the just price of things is not fixed with mathematical precision, but depends on a kind of estimate⁶

The judgement of the value of a thing in exchange seldom or never can be made except through conjecture or probable opinion, and not so precisely, or as if understood and measured by one invisible point, but rather as a fitting latitude within which the diverse judgements of men will differ in estimation.⁷

[it is] foolish to accept probable reasoning from a mathematician and to demand from a rhetorician scientific proofs.⁹

The most fundamental principle of all in gambling is simply equal conditions, e.g., of opponents, of bystanders, of money, of situation, of the dice box, and of the die itself. To the extent to which you depart from that equality, if it is in your opponent’s favour, you are a fool, and if in your own, you are unjust.¹⁰

A market is arbitrage free if and only if a martingale measure exists.

Fairness is based on equality.

is concerned with [man] solely as a being who desires to possess wealth, and who is capable of judging the comparative efficacy of means for obtaining that end.¹¹