Archive for higher order asymptotics

Jayanta Kumar Ghosh [1937-2017]

Posted in Books, pictures, Statistics, Travel, University life with tags , , , , , , , , on October 2, 2017 by xi'an

Just head from Sonia and Judith that our friend and fellow Bayesian Jayanta K Ghosh (জয়ন্ত কুমার ঘোষ in Bengali) has passed away a few days ago in Lafayette. He was a wonderful man, very kind to everyone and open for discussing all aspects of Bayesian theory and methodology. While he worked on many branches of statistics, he is more know to Bayesians for his contributions to Bayesian asymptotics. From Bernstein-von-Mises convergence theorems to frequentist validation of non-informative priors, to the Bayesian analysis of infinite dimensional problems, including consistency of posteriors and rates of convergence, and to Bayesian and Empirical Bayes model selection rules in high dimensional problems. He also wrote an introductory textbook on Bayesian Statistics ten years ago with Mohan Delampady and Tapas Samanta. And a monograph of higher order asymptotics. I knew from this summer that J K was quite sick and am quite sad to learn of his demise. He will be missed by all for his gentleness and by Bayesians for his contributions to the fields of objective and non-parametric Bayesian statistics…

workshop a Padova

Posted in pictures, R, Running, Statistics, Travel, University life with tags , , , , , , , , , , , , , on March 22, 2013 by xi'an

Needless to say, it is with great pleasure I am back in beautiful Padova for the workshop Recent Advances in statistical inference: theory and case studies, organised by Laura Ventura and Walter Racugno. Esp. when considering this is one of the last places I met with George Casella, in June 2010. As we have plenty of opportunities to remember him with so many of his friends here. (Tomorrow we will run around Prato della Valle in his memory.)

The workshop is of a “traditional Bayesian facture”, I mean one I enjoy very much: long talks with predetermined discussants and discussion from the floor. This makes for less talks (although we had eight today!) but also for more exciting sessions if the talks are broad and innovative. This was the case today (not including my talk of course) and I enjoyed the sessions a lot.

Jim Berger gave the first talk on “global” objective priors, starting from the desiderata to build a “general” reference prior when one does not want to separate parameters of interest from nuisance parameters and when one already has marginal reference priors on those parameters. This setting was actually addressed in Berger and Sun (AoS, 2008) and Jim presented some of the solutions therein: while I could not really see a strong incentive in using an arithmetic average of those, because it does not make much sense with improper priors, I definitely liked the notion of geometric averages, which evacuate the problem of the normalising constants. (There are open questions as well, about whether one improper prior could dwarf another one in the geometric average. Tail-wise for instance. Gauri Datta mentioned in his discussion that the geometric average is a specific Kullback-Leibler optimum.)

In his discussion of Tom Severini’s paper on integrated likelihood (which really stands at the margin of Bayesian inference), Brunero Liseo proposed a new use of ABC to approximate the likelihood function (while regular ABC relies on an approximation of the likelihood), a bit à la Chib. I cannot tell about the precision of this approximation but this is rather exciting!

Laura Ventura presented four of her current papers on the use of high order asymptotics in approximating (Bayesian) posteriors, following the JASA 2012 paper by Ventura, Cabras and Racugno. (The same issue featured a paper by Gill and Casella, coincidentally.) She showed the improvement brought by moving from first order (normal) to third order (non-normal). This is in a sense at the antipode of ABC, e.g. I’d like to see the requirements on the likelihood functions to be able to come up with a manageable Laplace approximation. She also mentioned a resolution of the Jeffreys-Lindley paradox via the Pereira et al. (2008) evidence, which computes a sort of Bayesian p-value by assessing the posterior probability of the posterior density being lower than its value at the null. I had missed or forgotten about this idea, but I wonder at some caveats like the impact of parameterisation, the connection with the testing problem, the calibration of the quantity, the extension to non-nested models, &tc. (Note that Ventura et al. developed an R package called hoa, for higher-order asymptotics.)

David Dunson presented some very recent work on compressed sensing that summed up for me into the idea of massively projecting (huge vectors of) regressors into much smaller dimension convex combinations, using random matrices for the projections. This point was somehow unclear to me. And to the first discussant Michael Wiper as well, who stressed that a completely random selection of those matrices could produce “mostly rubbish”, unless a learning mechanism was instated. The second discussant, Peter Müller, made the same point about this completely random search in a huge dimension space, while considering the survival frequency of covariates could help towards the efficiency of the method.