Unbiased Analysis of Today's Healthcare Issues

The Drunkard’s Walk

Written By: Jason Shafrin - Nov• 26•10

The Drunkard’s Walk is not about drinking.  Instead, as the subtitle states, the book discusses ‘How Randomness Rules our Lives.’  Although I personally didn’t enjoy this book, I highly recommend it to most people.

There are two categories of people who should not read this book: economists (me) statisticians, or mathematicians.  These people will likely already know most of the fundamental concepts which are outlined (in a very entertaining manner) in this book.  In addition, you should not read the book if you’ve read the History of Statistics (me).  The Drunkard’s Walk has a lot of neat anecdotes about the lives of statisticians and what problems they were trying to overcome wen they developed new statistical methods.  These anecdotes, however, are more thoroughly documented in the much denser, much slower, but also much more informative History of Statistics.

To see if you should read this book, check out the following excerpts below:

p. ix: “A few years ago a man won the Spanish national lottery with a ticket that ended in the number 48.  Proud of his “accomplishment,” he revealed the theory that brought him the riches. ‘I dreamed of the number 7 for seven straight nights,’ he said, ‘and 7 time 7 is 48.’

p. 10-11: “There exists a vast gulf of randomness and uncertainty between the creation of a great novel–or piece of jewelry or chocolate-chip cookie–and the presence of huge stacks of that novel–or jewelry or bags of cookies–at the front of thousands of retail outlets.  That’s why successful people in every field are almost universally members of a certain set–the set of people who don’t give up.

On the use of Bayesian Statistics for pricing care insurance: “Consider, for our purposes, a simplified model that places everyone in one of two categories: high risk…and low risk.  If when you apply for insurance, you have a driving record that stretches back twenty years without an accident or one that goes back twenty years with thirty-seven accidents, the insurance company can be pretty sure which category to place you in.  But if you are a new driver should you be classified as low risk…or high risk…?  Since the company has no data on you…it might…start you off by guessing that the changes you are a high risk are, say, 1 in 3.  In that case the company would model you as a hybrid–one-third high risk and two-thirds low risk–and charge you one-third the price it charges high risk drivers plus two-thirds the price it charges high risk drivers.  Then, after a year of observation…the company can employ the new datum to reevaluate its model, adjust the one-third and two-third proportions it previously assigned, and recalculate what it ought to charge.

You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

One Comment

  1. J Fuentes says:

    What are the chances that a book I just picked up, by chance, before the Thanksgiving break and began reading would be critiqued on my favorite health care blog? A probability calculation to tackle over the Christmas break.

    Although I am only half way through the book, I did enjoy the read and would also highly recommend it to most people, especially diagnosticians and medical students. In Chapter Six, titled False Positives and Postive Fallacies, Mlodinow provided us a first hand account of the importance of possessing a basic statistical competency to assess the usefulness (or futility) of diagnostic technologies.

    p. 115: “…When the added word husband’s proved to be the extent of the clues the kindhearted insurance company was willing to provide about our uninsurability, I went to my doctor on a hunch and took an HIV test. It came back positive. Though I was too shocked initially to quiz him about the odds he quoted, I later learned that he had derived my 1-in-1,000 chance of being healthy from the following statistic; the HIV test produced a positive result when the blood was not infected with the AIDS virus in only 1-in-1,000 blood samples. That might sound like the same message he passed on, but it wasn’t. My doctor had confused the chances that I would test positive if I was not HIV-positive with the chances that I would not be HIV-positive if I test positive.”

    Mlodinow clearly stated in the goal of his book in the Prologue; “to illustrate the role of chance in the world around us and to show how we may recognize it at work in human affairs”. This was a compelling personal account that demonstrates how some health care professionals, despite their extraordinary amount of training and expertise, can sometimes not fully appreciate the role of statistics in formulating their patient response/diagnosis. My guess is that if you ask most physicians or soon-to-be-physicians to explain the trade-offs involved in using highly-sensitive or highly-specific diagnostics, you might get the same look I gave my doctor when he told me I had a wedge fracture of the lateral tibial plateau with >5 mm depression which would require ORIF correction.

    Statistics does indeed play a critical role in understanding the world around us and its influence on our health, religious beliefs, education, families, and career, to name a few. Although a difficult topic to fully appreciate and understand, like Mlodinow, it might just give you the right tools to help you know when a death sentence is simply a false alarm. Who knows, the next time I undergo a diagnostic test, maybe I’ll avoid unnecessary disappointment by taking my results to a Dr. to be read, except this time, he/she will have a Ph.D. in Statistics.

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>