Following our earlier survey on the topic, we have now returned our report on the future of ISBA conferences to the ISBA Executive Committee and Guido Consonni wrote an extensive summary of the contents of this report for the ISBA Bulleting that just appeared. This is most timely since it comes just days prior to the ISBA World Meeting in Nagoya, Japan, with a discussion session on Thursday, during lunch break, where we will present the conclusions of this report and engage in discussions with the participants. Looking forward to it!
Archive for discussion
reporting on the future of ISBA conferences
Posted in Books, Kids, Travel, University life with tags committee work, discussion, inclusiveness, ISBA, ISBA 2026, Japan, mirror workshop, multi-hub conference, Nagoya on June 25, 2026 by xi'anBA webinar with discussion
Posted in Statistics with tags #BAjournal, ABC, Bayesian Analysis, conditional sampling, discussion, insufficiency, MCMC, restricted likelihood, webinar on February 8, 2022 by xi'an
likelihood-free inference by ratio estimation
Posted in Books, Mountains, pictures, Running, Statistics, Travel, University life with tags ABC, Austria, Bayesian lasso, Charlie Geyer, conflict of interest, Cross Validation, discussion, estimating constants, likelihood-free methods, logistic regression, nonparametrics, normalising constant, Salzburg, SimStat2019, summer, University of Warwick on September 9, 2019 by xi'an
“This approach for posterior estimation with generative models mirrors the approach of Gutmann and Hyvärinen (2012) for the estimation of unnormalised models. The main difference is that here we classify between two simulated data sets while Gutmann and Hyvärinen (2012) classified between the observed data and simulated reference data.”
A 2018 arXiv posting by Owen Thomas et al. (including my colleague at Warwick, Rito Dutta, CoI warning!) about estimating the likelihood (and the posterior) when it is intractable. Likelihood-free but not ABC, since the ratio likelihood to marginal is estimated in a non- or semi-parametric (and biased) way. Following Geyer’s 1994 fabulous estimate of an unknown normalising constant via logistic regression, the current paper which I read in preparation for my discussion in the ABC optimal design in Salzburg uses probabilistic classification and an exponential family representation of the ratio. Opposing data from the density and data from the marginal, assuming both can be readily produced. The logistic regression minimizing the asymptotic classification error is the logistic transform of the log-ratio. For a finite (double) sample, this minimization thus leads to an empirical version of the ratio. Or to a smooth version if the log-ratio is represented as a convex combination of summary statistics, turning the approximation into an exponential family, which is a clever way to buckle the buckle towards ABC notions. And synthetic likelihood. Although with a difference in estimating the exponential family parameters β(θ) by minimizing the classification error, parameters that are indeed conditional on the parameter θ. Actually the paper introduces a further penalisation or regularisation term on those parameters β(θ), which could have been processed by Bayesian Lasso instead. This step is essentially dirving the selection of the summaries, except that it is for each value of the parameter θ, at the expense of a X-validation step. This is quite an original approach, as far as I can tell, but I wonder at the link with more standard density estimation methods, in particular in terms of the precision of the resulting estimate (and the speed of convergence with the sample size, if convergence there is).
