I can’t remember who said this first, and I can’t remember if I’ve already put this on the blog, but the following definition may be helpful:

Every statistician uses Bayesian inference when it is appropriate (that is, when there is a clear probability model for the sampling of parameters). A *Bayesian statistician* is someone who will use Bayesian inference for all problems, even when it is inappropriate.

I am a Bayesian statistician myself (for the usual reason that, even when inappropriate, Bayesian methods seem to work well).

(The above is perhaps inspired by the saying that any fool can convict a guilty man; what distinguishes a great prosecutor is the ability to convict an innocent man.)

> even when inappropriate, Bayesian methods seem > to work well

The "pragmatic" Bayesian hypothesis.

Might be fun to write a grant proposal to "test" it.

Keith

p.s. nice summary of the recent Bayes/Non-Bayes posts

In what settings would you describe Bayesian methods as inappropriate even though they tend to work well? Perhaps a couple examples?

By "inappropriate," I mean setting where there is no reasonable sampling model for the parameters. Examples include just about all the examples in Bayesian Data Analysis.