## approximation of improper by vague priors

“…many authors prefer to replace these improper priors by vague priors, i.e. probability measures that aim to represent very few knowledge on the parameter.”

**C**hristèle Bioche and Pierre Druihlet arXived a few days ago a paper with this title. They aim at bringing a new light on the convergence of vague priors to their limit. Their notion of convergence is a pointwise convergence in the quotient space of Radon measures, quotient being defined by the removal of the “normalising” constant. The first results contained in the paper do not show particularly enticing properties of the improper limit of proper measures as the limit cannot be given any (useful) probabilistic interpretation. (A feature already noticeable when reading Jeffreys.) The first result that truly caught my interest in connection with my current research is the fact that the Haar measures appear as a (weak) limit of conjugate priors (Section 2.5). And that the Jeffreys prior is the limit of the parametrisation-free conjugate priors of Druilhet and Pommeret (2012, Bayesian Analysis, a paper I will discuss soon!). The result about the convergence of posterior means is rather anticlimactic as the basis assumption is the uniform integrability of the sequence of the prior densities. An interesting counterexample (somehow familiar to invariance fans): the sequence of Poisson distributions with mean n has no weak limit. And the Haldane prior does appear as a limit of Beta distributions (less surprising). On (0,1) if not on [0,1].

The paper contains a section on the Jeffreys-Lindley paradox, which is only considered from the second perspective, the one I favour. There is however a mention made of the noninformative answer, which is the (meaningless) one associated with the Lebesgue measure of normalising constant one. This Lebesgue measure also appears as a weak limit in the paper, even though the limit of the posterior probabilities is 1. Except when the likelihood has bounded variations outside compacts. Then the limit of the probabilities is the prior probability of the null… Interesting, truly, but not compelling enough to change my perspective on the topic. *(And thanks to the authors for their thanks!)*

November 18, 2013 at 2:38 pm

Maybe I’m measure-theoretically naïve, but I really liked this paper just because it gives a crisp definition of a (quotient) space where sequences of probability measures approaching an improper sigma-finite measure limit makes some kind of sense.

(I have a problem lingering in the back of my mind where this kind of convergence is exactly what I need. It relates to decision theory on set estimators — a while back I emailed you about some of your early work relating to these kinds of things.)

November 18, 2013 at 3:11 pm

sorry, Corey, for bypassing this email! Could you send it again?!

November 18, 2013 at 7:11 pm

You didn’t bypass it — you replied that you didn’t have a copy of the doc I was looking for.