Another day at O’Bayes 2013, recovering from the flow of reminiscences of yesterday. Talks from Guido Consonni on running reference model selection in complex designs, from Dimitris Fouskakis on integrating out imaginary observations in a g-prior, which seems to bring more sparsity than the hyper-g prior in variable selection, from François Perron on Bayesian inference for copulas, with an innovative parametrisation and links with Polya trees, from Nancy Reid and Laura Ventura on likelihood approximations and pseudo-likelihoods, offering a wide range of solutions for ABC (or BC) references (with the lingering question of the validation of the approximation for a given sample, as discussed by Brunero Liseo) and from two physicists to conclude the day! Tomorrow is the final day and I hope I can go running a last time in the woods before the flights back to Paris.
Archive for pseudo-likelihood
O’Bayes 2013 [#2]
Posted in pictures, Running, Statistics, Travel, University life with tags copulas, Duke University, Durham, ISBA, O-Bayes 2013, physics, pseudo-likelihood, reference priors on December 19, 2013 by xi'anJulian Besag memorial
Posted in Statistics, Travel, University life with tags Bristol, Gibbs sampling, Hammersley-Clifford theorem, Julian Besag, MCMC, pseudo-likelihood, spatial statistics on April 3, 2011 by xi'an
Homme libre, toujours tu chériras la mer!
La mer est ton miroir; tu contemples ton âme
Dans le déroulement infini de sa lame,
Et ton esprit n’est pas un gouffre moins amer.
Charles Baudelaire, Les Fleurs du Mal
The first afternoon of the memorial session for Julian Besag in Bristol was an intense and at times emotional moment, where friends and colleagues of Julian shared memories and stories. This collection of tributes showed how much of a larger-than-life character he was, from his long-termed and wide-ranged impact on statistics to his very high expectations, both for himself and for others, leading to a total and uncompromising research ethics, to his passion for [extreme] sports and outdoors. (The stories during and after diner were of a more personal nature, but at least as much enjoyable!) The talks on the second day showed how much and how deeply Julian had contributed to spatial statistics and agricultural experiments, to pseudo-likelihood, to Markov random fields and image analysis, and to MCMC methodology and practice. I hope I did not botch too much my presentation on the history of MCMC, while I found reading through the 1974, 1986 and 1993 Read Papers and their discussions an immensely rewarding experiment (I wish I had done prior to completing our Statistical Science paper, but it was bound to be incomplete by nature!). Some interesting links made by the audience were the prior publication of proofs of the Hammersley-Clifford theorem in 1973 (by Grimmet, Preston, and Steward, respectively), as well as the proposal of a Gibbs sampler by Brian Ripley as early as 1977 (even though Hastings did use Gibbs steps in one of his examples). Christophe Andrieu also pointed out to me a very early Monte Carlo review by John Halton in the 1970 SIAM Rewiew, review that I will read (and commment) as soon as possible. Overall, I am quite glad I could take part in this memorial and I am grateful to both Peters for organising it as a fitting tribute to Julian.
