The Theory That Would Not Die – McGrayne, Sharon B – Yale University Press

The Theory That Would Not Die – McGrayne, Sharon B – Yale University Press.

This great book arrived just in time for a Summer read. The first chapter gives an account of the Rev. Thomas Bayes (it’s clear from the book that for example Hume’s skepticism, which interestingly originates in reservations about cause and effect) provided part of the environment leading Bayes to study inverse probability. The professional circles he worked in, especially in Tunbridge Wells are colourfully described. Ultimately however, it describes how Price published his work, and more importantly the next chapter describes how Laplace really set out a theory of inverse probability. Notably, he described probability as “common sense reduced to mathematics”.

The book then gets very interesting. There is a strong account of the rise of frequents (Ziliak and McCloskey seem to make similar points about many of the characters in their “Cult of Statistical Significance”. The book examines many mid 20th century developments, and of course looks at how computer power, and particularly McMC have made routine Bayesian data analysis possible.

The title however plays on wartime applications of Bayes theorem. There is talk of the real search for Red October, and the entirely non-fictional search for missing US nuclear weapons. However, it appears that any advocacy gains were pyrrhic. The more interesting applications surround decryption, and particularly Turing’s work at Bletchley Park – specifically for example noting that Turing’s Banburismus used units of one Ban (or milli-bans) based on use of Bayes Theorem. There were even hints that the cryptographers were using Bayes theorem all the time, but playing down it’s value in the interests of national security. That would be rather ironic given that Kolmogorov seems to have been able to publish his work on optimal artillery strategies (I gees either no one appreciated the implications, or else they worked on the assumption that the “enemy” wouldn’t read a Russian language journal).

All in all, very enjoyable read, with lots of biographical details about many of the players.

This entry was posted in Bayesian philosophy. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s