Archive for Theory of Probability

Jeffreys priors for hypothesis testing [Bayesian reads #2]

Posted in Books, Statistics, University life with tags , , , , , , , , , , , , , , , , on February 9, 2019 by xi'an

A second (re)visit to a reference paper I gave to my OxWaSP students for the last round of this CDT joint program. Indeed, this may be my first complete read of Susie Bayarri and Gonzalo Garcia-Donato 2008 Series B paper, inspired by Jeffreys’, Zellner’s and Siow’s proposals in the Normal case. (Disclaimer: I was not the JRSS B editor for this paper.) Which I saw as a talk at the O’Bayes 2009 meeting in Phillie.

The paper aims at constructing formal rules for objective proper priors in testing embedded hypotheses, in the spirit of Jeffreys’ Theory of Probability “hidden gem” (Chapter 3). The proposal is based on symmetrised versions of the Kullback-Leibler divergence κ between null and alternative used in a transform like an inverse power of 1+κ. With a power large enough to make the prior proper. Eventually multiplied by a reference measure (i.e., the arbitrary choice of a dominating measure.) Can be generalised to any intrinsic loss (not to be confused with an intrinsic prior à la Berger and Pericchi!). Approximately Cauchy or Student’s t by a Taylor expansion. To be compared with Jeffreys’ original prior equal to the derivative of the atan transform of the root divergence (!). A delicate calibration by an effective sample size, lacking a general definition.

At the start the authors rightly insist on having the nuisance parameter v to differ for each model but… as we all often do they relapse back to having the “same ν” in both models for integrability reasons. Nuisance parameters make the definition of the divergence prior somewhat harder. Or somewhat arbitrary. Indeed, as in reference prior settings, the authors work first conditional on the nuisance then use a prior on ν that may be improper by the “same” argument. (Although conditioning is not the proper term if the marginal prior on ν is improper.)

The paper also contains an interesting case of the translated Exponential, where the prior is L¹ Student’s t with 2 degrees of freedom. And another one of mixture models albeit in the simple case of a location parameter on one component only.

Гнеде́нко and Forsythe [and e]

Posted in Books, Kids, R, Statistics, University life with tags , , , , , , , , on February 16, 2016 by xi'an

In the wake of my earlier post on the Monte Carlo estimation of e and e⁻¹, after a discussion with my colleague Murray Pollock (Warwick) Gnedenko’s solution, he pointed out another (early) Monte Carlo approximation called Forsythe’s method. That is detailed quite neatly in Luc Devroye’s bible, Non-uniform random variate generation (a free bible!). The idea is to run a sequence of uniform generations until the sequence goes up, i.e., until the latest uniform is larger than the previous one. The expectation of the corresponding stopping rule, N, which is the number of generations the uniform sequence went down continuously is then e, while the probability that N is odd is e⁻¹, most unexpectedly! Forsythe’s method actually aims at a much broader goal, namely simulating from any density of the form g(x) exp{-F(x)}, F taking values in (0,1). This method generalises von Neuman’s exponential generator (see Devroye, p.126) which only requires uniform generations.

gnevsforsThis is absolutely identical to Gnedenko’s approach in that both events have the same 1/n! probability to occur [as pointed out by Gérard Letac in a comment on the previous entry]. (I certainly cannot say whether or not one of the authors was aware of the other’s result: Forsythe generalised von Neumann‘s method around 1972, while Gnedenko published Theory of Probability at least in 1969, but this may be the date of the English translation, I have not been able to find the reference on the Russian wikipedia page…) Running a small R experiment to compare both distributions of N, the above barplot shows that they look quite similar:

n=1e6
use=runif(n)
# Gnedenko's in action:
gest=NULL
i=1
while (i<(n-100)){
sumuse=cumsum(use[i:(i+10)])
if (sumuse[11]<1]) 
  sumuse=cumsum(use[i:(i+100)]) 
j=min((1:length(sumuse))[sumuse>1])
gest=c(gest,j)
i=i+j}
#Forsythe's method:
fest=NULL
i=1
while (i<(n-100)){
sumuse=c(-1,diff(use[i:(i+10)]))
if (max(sumuse)<0]) 
  sumuse=c(-1,diff(use[i:(i+100)])) 
j=min((1:length(sumuse))[sumuse>0])
fest=c(fest,j)
i=i+j}

And the execution times of both approaches [with this rudimentary R code!] are quite close.

re-revisiting Jeffreys

Posted in Books, pictures, Statistics, Travel, University life with tags , , , , , , , on October 16, 2015 by xi'an

Amster12Analytic Posteriors for Pearson’s Correlation Coefficient was arXived yesterday by Alexander Ly , Maarten Marsman, and Eric-Jan Wagenmakers from Amsterdam, with whom I recently had two most enjoyable encounters (and dinners!). And whose paper on Jeffreys’ Theory of Probability I recently discussed in the Journal of Mathematical Psychology.

The paper re-analyses Bayesian inference on the Gaussian correlation coefficient, demonstrating that for standard reference priors the posterior moments are (surprisingly) available in closed form. Including priors suggested by Jeffreys (in a 1935 paper), Lindley, Bayarri (Susie’s first paper!), Berger, Bernardo, and Sun. They all are of the form

\pi(\theta)\propto(1+\rho^2)^\alpha(1-\rho^2)^\beta\sigma_1^\gamma\sigma_2^\delta

and the corresponding profile likelihood on ρ is in “closed” form (“closed” because it involves hypergeometric functions). And only depends on the sample correlation which is then marginally sufficient (although I do not like this notion!). The posterior moments associated with those priors can be expressed as series (of hypergeometric functions). While the paper is very technical, borrowing from the Bateman project and from Gradshteyn and Ryzhik, I like it if only because it reminds me of some early papers I wrote in the same vein, Abramowitz and Stegun being one of the very first books I bought (at a ridiculous price in the bookstore of Purdue University…).

Two comments about the paper: I see nowhere a condition for the posterior to be proper, although I assume it could be the n>1+γ−2α+δ constraint found in Corollary 2.1 (although I am surprised there is no condition on the coefficient β). The second thing is about the use of this analytic expression in simulations from the marginal posterior on ρ: Since the density is available, numerical integration is certainly more efficient than Monte Carlo integration [for quantities that are not already available in closed form]. Furthermore, in the general case when β is not zero, the cost of computing infinite series of hypergeometric and gamma functions maybe counterbalanced by a direct simulation of ρ and both variance parameters since the profile likelihood of this triplet is truly in closed form, see eqn (2.11). And I will not comment the fact that Fisher ends up being the most quoted author in the paper!

Conditional love [guest post]

Posted in Books, Kids, Statistics, University life with tags , , , , , , , , , , , , , , , , , , , , on August 4, 2015 by xi'an

[When Dan Simpson told me he was reading Terenin’s and Draper’s latest arXival in a nice Bath pub—and not a nice bath tub!—, I asked him for a blog entry and he agreed. Here is his piece, read at your own risk! If you remember to skip the part about Céline Dion, you should enjoy it very much!!!]

Probability has traditionally been described, as per Kolmogorov and his ardent follower Katy Perry, unconditionally. This is, of course, excellent for those of us who really like measure theory, as the maths is identical. Unfortunately mathematical convenience is not necessarily enough and a large part of the applied statistical community is working with Bayesian methods. These are unavoidably conditional and, as such, it is natural to ask if there is a fundamentally conditional basis for probability.

Bruno de Finetti—and later Richard Cox and Edwin Jaynes—considered conditional bases for Bayesian probability that are, unfortunately, incomplete. The critical problem is that they mainly consider finite state spaces and construct finitely additive systems of conditional probability. For a variety of reasons, neither of these restrictions hold much truck in the modern world of statistics.

In a recently arXiv’d paper, Alexander Terenin and David Draper devise a set of axioms that make the Cox-Jaynes system of conditional probability rigorous. Furthermore, they show that the complete set of Kolmogorov axioms (including countable additivity) can be derived as theorems from their axioms by conditioning on the entire sample space.

This is a deep and fundamental paper, which unfortunately means that I most probably do not grasp it’s complexities (especially as, for some reason, I keep reading it in pubs!). However I’m going to have a shot at having some thoughts on it, because I feel like it’s the sort of paper one should have thoughts on. Continue reading

the (expected) demise of the Bayes factor [#2]

Posted in Books, Kids, pictures, Running, Statistics, Travel, University life with tags , , , , , , , , , on July 1, 2015 by xi'an

AmsterXXFollowing my earlier comments on Alexander Ly, Josine Verhagen, and Eric-Jan Wagenmakers, from Amsterdam, Joris Mulder, a special issue editor of the Journal of Mathematical Psychology, kindly asked me for a written discussion of that paper, discussion that I wrote last week and arXived this weekend. Besides the above comments on ToP, this discussion contains some of my usual arguments against the use of the Bayes factor as well as a short introduction to our recent proposal via mixtures. Short introduction as I had to restrain myself from reproducing the arguments in the original paper, for fear it would jeopardize its chances of getting published and, who knows?, discussed.