Feb

6

Ronald FisherSo… I have studied the foundations of Statistics. Gone back to first principles. I am now convinced that the Bayesian approach is the way to go. It makes much more (common) sense than the rest.

The only reason Statistics today is not 100% Bayesian, is that the Reverend's paradigm has been made practical only recently, with the growth of computer power and the discovery of some really clever algorithms (Gibbs sampling etc…).

My idol, role-model, who I hold totally admire and who keeps me in a state of awe, Ronald Fisher, was a Bayesian. It is not obvious until you read his original articles, but he was. He was also a nice person in a time before computers, so he developed some simple not-entirely-Bayesian solutions to help mankind.

Bayesian statistics is the way to go… Only problem is that I have come to realize I know very little about them beyond basics.

My program for 2010 is to master Bayesian statistics. By "mastering" I mean being able to read a PhD thesis, but not necessarily to write one (I have a life).

There are many great statisticians on this list that could advise me on some books. I think Vic is a great Statistician, and Fisherian/Bayesian even if he doesn't realize it.

So far I have read:

Bayesian Computation with R Albert
Bayesian Data Analysis Gelman & Carlin & Stern & Rubin
Bayesian Forecasting and Dynamic Models West & Harrison
Introduction to Bayesian Statistics Bolstad
Introduction to Modern Bayesian Econometrics Lancaster

What I need now is to know what are the best books in the field, and some form of advice on progression, the above books being a bit of a strange mix between obvious and difficult.

If you were a university teacher, what books would you require your students to read and in what order?

And should I read the original articles from the 1950s advocates, eg Savage, De Finetti or Jeffreys?


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search