Notes on The Drunkard's Walk - But Not Really

The Drunkard's Walk: How Randomness Rules Out Lives

Leonard Mlodinow, 2008

I was pretty disappointed overall because he doesn't talk about the drunkard's walk until the last chapter. No saccades, no Levy-walks, no foraging behavior or network science. Just another boring-ass book about the same old stuff that always gets the same average people excited, because they've never yet in their lives heard of cognitive fallacies or the law of large numbers. I wanted to learn about randomness - tell me something about procedurally-generated video games or quantum random number generators. Tell me things that I don't already know. Or at least tell me about the thing that titled the book. Alas, this book was not for me.

Regardless, some notes:

• Cicero on Astrology (which he did not like, as he was a man of numbers) - "Did all the Romans who fell at Cannae have the same horoscope? Yet all had one and the same end." (p32) -Cicero quoted in F. N. David, "Gods, Games and Gambling: A History of Probability and Statistical Ideas (Mineola, N.Y.:Dover Publications, 1998), pp.24-26
• On the law of large numbers and just statistics in general - John Kerrich, South African mathematician, 1940's, flips a coin 10,000 times. (he was a prisoner of war at the time). After 100 throws he had 44 heads; by 10,000 he had 5,067 heads. (p95) -Statistics by David Freedman, Robert Pisani and Roger Purves in 1998. pp274-275
• Bayes conditional probability and conspiracy theories: they depend on confusing the probability that a series of events would happen IF it were the product of a huge conspiracy with the probability that a huge conspiracy exists IF a series of events occurs (p107); OR LIKE a guy that beats his wife is also a cop VS a guy that's a cop that also beats his wife; OR a husband would sneak around IF he were having an affair VS a husband having an affair IF he were sneaking around; OR a person is mentally ill if he believes they're after him VS a person is being targeted if he is mentally ill. (One of these is way more probable than the other, and because of Bayesian conditional probability.)

• (I'm being petty here, but I find it funny that the author uses the 1963 wine-color study to talk about cognitive override, which is a bad study anyway because it intentionally tricks experts who are trained to use BOTH color AND taste to do their job, but then in 2008 another wine study was done  using MRI and found they actually liked the more expensive wines more; but in reality recent studies in neuroscience show that any MRI studies with less than 1,000 participants can't produce statistically significant results due to natural variation among brains, so this study being used in a book about statistics is ironic.)

• 1850's "table moving" as emergent phenomenon (p170)
• -Ray Hyman, "Parapsychological Research: A Tutorial Review and Critical Appraisal," Proceedings of the IEEE 74, no. 6 (June 1986): 823-49.
• -Michael Faraday, "Experimental Investigation of Table-Moving" Athenaeum, July 2, 1853, pp.801-3.

• One of the most well-known contemporary examples of randomness - the iPod shuffle (p175)

• Stocks - "There is much evidence, for instance, that the performance of stocks is random -- or so close to being random that in the absence of insider information and in the presence of a cost to make trades or manage your portfolio, you can't profit from any deviations from randomness. (p176) -Burton G. Malkiel, A Random Walk Down Wall Street, 2003 edition
• Stocks cont'd - Nevertheless, Wall Street has a long tradition of guru analysts, and the average analyst's salary, at the end of the 1900's was about $3 million (ft 15). How do these analysts do? According to a 1995 study, the eight to twelve most highly paid "Wall Street Superstars" invited by Barron's to make market recommendations at its annual roundtable merely matched the average market return (ft 16). Studies in 1987 and 1997 found that stocks recommended by the prognosticators on the television show Wall Street Week did much worse, lagging far behind the market (ft 17). And in a study of 153 newsletters, a researcher at Harvard Institute of Economic Research found "no significant evidence of stock-picking ability." (ft 18) (p176)

15. Investment Blunders of the Rich and Famous, John R Nofsinger, 2002

16. An Analysis of the Recomendations of the 'Superstar' money Managers at Barron's Annual Roundtable, Hemang Desai and Prem C. Jain, 1995

17. Wall $treet Week with Louis Rukeyser's Recommendations: Trading Activity and Performance, Jess Beltz and Robert Jennings, 1997; Wall $treet Week Recommendations: Yes or No?, robert A Pari, 1987

18. Performance Evaluation with Transactions Data: The Stock Selection of Investment Newsletters, Andrew Matrick, 1999; The Equity Performance of Investment Newsletters, 1997