See us hosts and the blogs we’ve chosen to review at this site coordinated by John. As you can see, StatsMadeEasy is culling the best of these bloggers:

• Bob Sutton (“Work Matters”)
• Seth Godin
• Justin Hunter (Hexawise Blog)*

This last blog – one of many proffered by John that focus on agile programming – is reviewed by my son Hank, who codes for Stat-Ease.

Bob Sutton offers many impressive credentials but the one that caught my eye was Weird Ideas That Work – a book he authored. I’m always on the lookout for non-intuitive approaches that improve process effectiveness. One of Sutton’s suggestions is to “increase variance in available knowledge.” That’s a good twist for an aficionado of stats!

Here my favorite 2009 posts by Bob:

• 1/20, Brainstorming: Pros and Cons provides a balanced view of whether it works to gather a group for generation of ideas. I’ve been intrigued by this since my days as a Product Manager at General Mills (chemical division) when I would lead brainstorms with our R&D scientists and engineers. Note the comment by blogger Keith Harmeyer (SmartStorming) that “the ideal situation is a combination of solo ideation and brainstorming.” I agree with that because it draws out ideas from the introverts — perhaps propensity to speak one’s mind is inversely correlated to quality of comment. ; )
• 3/9 Dilbert and The Smart Talk Trap re-tells a story from Weird Ideas That Work in which a brainstorming leader at Microsoft asked “What would be the worst product we could possibly build?” His idea was to think opposite but, of course, the crazy idea is what management liked. Coincidentally I was watching the movie Revolutionary Road, which features a cynical worker in a downtrodden ‘50s office (played wonderfully by Leonard DiCaprio) who, after deciding to quit this rat race, fires off a flippant flyer to the Toledo branch. This then gets him a promotion for thinking out of the box!
  

  “Ideas that seem dumb may have more merit than you think.” – Bob Sutton

• 7/6 Wisdom, Randomness, and the Naskapi Indians provides a good example of how one can often benefit by choosing a direction at random. This works well for me when deciding at poker game whether to bluff or not. I won’t say anything more because one of my buddies might read this, so it would cost me.
• 10/7/09 Squeaky Wheels, The Health Care Debate, and Student Complaints About Grades reveals how Sutton, a professor at Stanford University, deals with students who complain about grades. Being a stoic Minnesotan who was taught to grin and bear it, I like his thinking on this!
• 11/1/09 Intuition vs. Data-Driven Decision-Making: Some Rough Ideas supports Sutton’s view “that intuition and analysis are not opposing perspectives, but tag team partners that, under the best conditions, where hunches are followed and then evaluated with evidence…” My world of statistical design of experiments is data driven, of course. However, the big breakthroughs in process and product improvement often come from subject-matter experts who come up with a brilliant hunch that pans out. The classic book on DOE Statistics for Experimenters, co-authored by Bill Hunter (the father of John Hunter who is the ring-master for this carnival of blogs), begins with a wonderful treatise on induction versus deduction that I recommend to all experimenters.

I would be remiss not to provide a heads up to the elephant in the room at the Work Matters blog: Sutton devotes many of his posts to the bad behavior of bosses – a bugaboo for me too. The difference is that I keep my expletive (***hole!!!) private, whereas Sutton is brave enough to shout it out. Most of you may find this scintillating, but those who consider prim to be professional: Be forewarned about some rough language. One of the tamer and thought-provoking posts (29 comments) is the October 18th one asking Do You Learn More from Working for a Bad Boss than a Good Boss? Another post that takes the high road came on December 22 (just the other day) relating The Boss’s Journey: The Path to Simplicity and Competence. Being of a certain age (not far from Bob’s) I had to chuckle at his story of a student who disrespected managers until becoming the boss of a small product development team made him realize how hard this role can be.

Perhaps this holiday season you may restrict yourself to tamer drinks than high-alcohol beer, such as the traditional eggnog — a “sweetened dairy-based beverage made with milk, cream, sugar, beaten eggs (which gives it a frothy texture), and flavored with ground cinnamon” (according to Wikipedia).  However, my plans to pick up our annual eggnog after Thanksgiving were dashed after listening to a recent radio broadcast of NPR’s Science Friday by Ira Flatow.  They warned about people (like me) risking salmonella-induced food poisoning by milking their ‘nog clear through Christmas.  The show posted this video reporting results from microbiologist Vince Fischetti on his challenge tests** in a lab at the Rockefeller University (RU).  I’ve seen these at food clients of Stat-Ease and they gross me out, so I know the end result of dosing up a dairy product with spoilage organisms and pathogens cannot be pretty.  Fischetti compared the results after one month of storing a spiked eggnog made by a traditional RU recipe (equal parts bourbon and rum to a 20 % alcohol level) versus one purchased commercially (no alcohol).  See the outcome by watching the video – it may encourage you to keep a bottle of spirits on hand.  (I’ve got a supply of tequila – just in case.)  Being a devotee of DOE, I must say that Fischetti’s findings appear to be based only on sample-size 1.  But to his credit, he expresses the desire for grant money leading to more definitive studies.

So whether you hoist a beer or a ‘cheered-up’ glass of eggnog to give your seasonal salute to your friends and family, here’s hoping you all a happy holiday!

*Source for news about high-alcohol beer: 11/30/09 article by Russell Contreras of the Associated Press, seen here as published by the Huffington Post.

** For all the gory details see this posting of Microbiological Challenge Testing by the Institute of Food Technologists (IFT).  The “Phoenix” phenomenon is particularly worrying (lethal bugs rising from the ashes of sterilization).

Our local newspaper headlined this report with the suggestion that we Minnesotans “try living in a sunnier State.”  I have a hard time arguing with moving to Hawaii or Florida – both near the top the Oswald-Wu list.  Louisiana (#1) is a good choice too, I think, despite the setback of Hurricane Katrina.  I spent time there and in the neighboring State of Mississippi (#7) last March – a great time to get out of Minnesota (#26).  However, I really do enjoy our winters here in the northernmost part of the lower 48.  At this time of the year our sun sits nearly at its lowest point (Winter solstice being mid-day tomorrow), which makes any rays one can catch all the more dear.

This morning a little Canadian ‘clipper’ topped off our existing blanket of snow with another inch of sun-sparkled crystals.  It was good to be outdoors walking the dog through our little “Sunwood” park of evergreens again after taking a little break on our daily strolls last week due to the bitter cold.  Maybe it was just as well we stayed home because a cougar came through our neighborhood (called “Croixwood”) as evidenced by the huge paw print pictured here .  The cougar was last sighted in Wisconsin.  My guess is that this cat is headed for Florida. =^.^=

Perhaps the size of this creature is explained by findings of marine geologist Justin Ries of the University of North Carolina, who reports that rising levels of atmospheric carbon dioxide may lead to larger crabs, shrimp and lobsters.

See a summary of Ries’s research and a picture of a monster lobster in this post by NPR.   Wow, these exoskeletoned creatures really like carbon!

PS. All this talk of large lobsters reminds me of an illustration of evolutionary operation (EVOP) by Box and Draper.*  Their process improvement method calls an ongoing series of two-level factorial designs that illuminate a path to more desirable manufacturing conditions.  I will talk more about this in a future blog.

*Box, G. E. P. and N. R. Draper, Evolutionary Operation, Wiley New York, 1969.  (Wiley Classics Library, paperback edition, 1998.)

“Highly qualified students may be choosing a non-STEM job because these other occupations are higher paying, offer better career prospects such as advancement, employment stability, and/or prestige…”

– B. Lindsay Lowell, Hal Salzman, Hamutal Bernstein, with Everett Henderson

Stat-Ease specializes in design of experiments (DOE) for industrial research.  Therefore, the more who stay with STEM the better, so far as I’m concerned.   However, I plead guilty to going for the money by pursuing a master’s degree in business administration.  This led to me being promoted out of my chemical engineering job in R&D to a position as product manager.  My business partner Pat Whitcomb went for a master’s in chemical engineering, thus sticking with STEM.  He and I enjoy ribbing each other about our diverging paths, but it turned out to be very synergistic having these complementary mindsets (technical versus business).  I figure that in high-tech companies like ours, it can’t hurt to have managers with a STEM degree, at least undergraduate, thus it may not be worth trying to stem this tide.

*See Figure 4 from this October 2009 report on three generations of students by researchers (quoted above) from Georgetown, Rutgers and The Urban Institute.

PS. The STEM Education Coalition co-chaired by the American Chemical Society (ACS) and the National Science Teachers Association works to maintain the USA’s edge in technology – primarily via K-12 education..  The American Statistical Association (ASA) is a participating organization along with dozens of others in the fields of science, technology, engineering and math.

Earlier this week we stopped by an interesting museum in Apalach’ (as the locals refer to it).  It celebrates the achievements of a local physician, John C. Gorrie, who invented the ice-making machine.  He is also considered to be the father of refrigeration and air conditioning.  Obviously the folks here in Florida hold Dr. Gorrie in high esteem for his dedication to cooling things off.  What interests me, being that I am a chemical engineer, is how steam powered Gorrie’s ice machine.  That seems very counter-intuitive, but the thermodynamics are explained nicely here by the inventor:

“If the air were highly compressed, it would heat up by the energy of compression. If this compressed air were run through metal pipes cooled with water, and if this air cooled to the water temperature was expanded down to atmospheric pressure again, very low temperatures could be obtained, even low enough to freeze water in pans in a refrigerator box.”

For a picture of what he patented in 1851 and historical background, see this Wired magazine article by Randy Alfred.

Getting back to the Thanksgiving feast this afternoon and thinking about the oysters,  I suppose we will be given a choice of raw ones laid out on ice (thanks to the local inventor) or one cooked with steam.  Coming from the middle of our continent, it may be too much of a stretch to eat uncooked shellfish.  In fact, it makes me a bit queasy just thinking of it.  Although I fancy myself an experimentalist, sometimes I must draw a line in the sand.

PS. One thing I find curious is that the oystermen (sorry ladies) still do their harvesting the old-fashioned way with tongs – see this video, for example .

Supposedly this left-to-right approach makes it easier for children to learn, because it goes in the same direction for processing numbers as for reading words. Here’s how it works.  Let’s say that you and your spouse both collect up pennies and the first jar nets 237 cents versus 159 for the second.  How much in total can be taken to the bank? The way I learned to add one first adds 7 and 9, recording 6 as the right-most digit (the ones column), and then carrying a 1 to the second column (the tens).  This carrying part is where I sometimes get off, mainly due to my poor handwriting, which even I cannot always read.  The new left-to-right approach eliminates a lot of carrying, but not all, I figure, as shown in the following case.  Start by adding the left-most (hundreds in this case) column of numbers:
   247
+159
=300

Do not forget to put in the zeroes to hold the place of what you just added.  Now go to the next column to the right and add it:
= 90 (4 + 5)

And so forth until there’s no more columns:
= 16 (7 + 9)

Finally, tally up all the numbers you calculated:
300
+90
+16
406

I have a feeling that the old saying about not trying to teach an old dog new tricks might be operative for me in regard to this new math.  I think I will just keep adding the old way, or admit that using a calculator or, better yet, a computerized spreadsheet for doing my deposits would be smarter.  Am I shortchanging myself (pun intended)?

PS. This innovation in learning math struck a chord with my son Hank, who programs for Stat-Ease.  He made me aware that “endianness” is a major issue in coding.  Evidently programmers continually feud over the order in which bytes in multi-byte numbers should be stored – most-significant first (Big-Endian) or least-significant first (Little-Endian).*  The “endian” terms come from Jonathan Swift who mocked the pettiness of social customs, such as which end one ought to first attack when shelling an egg.

“…the primitive way of breaking Eggs, before we eat them, was upon the larger End: But his present Majesty’s Grand-father, while he was a Boy, going to eat an Egg, and breaking it according to the ancient Practice, happened to cut one of his Fingers. Whereupon the Emperor his Father published an Edict, commanding all his Subjects, upon great Penaltys, to break the smaller End of their Eggs.”
– Jonathan Swift, Gulliver’s Travels, A Voyage to Lilliput, Chapter IV.

*For more details, see Basic concepts on Endianness.

This week I did my day on DOE (design of experiments) for a biannual workshop on Lean Six Sigma sponsored by Ohio State University’s Fisher College of Business (blended with training by www.MoreSteam.com.)  Early on I present a case study* on a training experiment done by a software publisher.  The goal is to increase the productivity of programmers by sending them to workshop.  The manager asks for volunteers from his staff of 30.  Half agree to go.  Upon their return from the class his annual performance rating, done subjectively on a ten-point scale, reveals a statistically significant increase due to the training.  I ask you (the same as I ask my lean six sigma students): Is this fair?

“Designing an experiment is like gambling with the devil: only a random strategy can defeat all his betting systems.”

– RA Fisher

PS. I put my class to the test of whether they really “get” how to design and analyze a two-level factorial experiment by asking them to develop a long-flying and accurate paper helicopter.  They use Design-Ease software, which lays out a randomized plan.  However, the student tasked with dropping the ‘copters of one of the teams just grabbed all eight of their designs and jumped up the chair.  I asked her if she planned to drop them all at once, or what.  She told me that only one at a time would be flown – selected by intuition as the trials progressed.  What an interesting sampling strategy!

PPS. Check out this paper “hella copter” developed for another statistics class (not mine).

*(Source: “Design of Experiments, A Powerful Analytical Tool” by Christopher Nachtsheim and Bradley Jones, Six Sigma Forum Magazine, August 2003.)

I like the idea of this being a blind analysis, although I wonder if these four statisticians might’ve seen through this.  Also, what is a good sample size for statisticians?  Four seems meager.  Do you pick statisticians at random, or what?

Anyways, I am more concerned about my Minnesota Gophers going to a new outdoor stadium in what will turn out to be one of the coldest Octobers ever in this region.  They play Saturday night, which is Halloween – scary enough on a college campus –but it might be wickedly cold as well.  Fortunately I have a good collection of Gopher shirts, sweats and jackets to put on layer-by-layer.  I noticed something funny about being outdoors after so many years of under the Metrodome: People clapping with mittens on just doesn’t work as well for cheering purposes.