Thanks to Florence Forbes, who was also celebrating Adrian Raftery’s carreer (so far!), I became aware the day before that there would be a 10k race in down-town Seattle, around Lake Union, Sunday morning, and decided to join, despite the hefty entry fees (although reduced for seniors like me!), and with a rather poor week, training-wise. With the impression that it was an easier race than the week before, being mostly flat… After a very fast, too fast, start, I began to feel belly pains, which forced me to stop twice by convenient bushes and to slow down to standard training times (despite keeping to 20mn at the 5k mark). A counter-performance, when I could have been among the 20 first runners with last week time (39:26). I wonder what is the origin for these belly issues, between having drunk (a small amount of) beer the previous evening, eaten deep-fried oysters the previous lunch (on Seattle harbour), swam in Lake Washington (with otters!!) the previous morning, or simply opting for a cereal breakfast too close to the time of the race… In addition, my time did not get recorded properly and I got listed as non-finisher, missing the podium in my age group. Oh well, not all races can be great and enjoyable!
Archive for Adrian Raftery
when bib, beer, bug, bran, and belly unite [Lake Union 10k, 43:18, 84/1770, 2/33 M61-70]
Posted in pictures, Running, Travel with tags 10k, Adrian Raftery, Lake Union, road race, Seattle, University of Washington, USA, Washington State on August 23, 2024 by xi'ancelebrating the career of Adrian Raftery
Posted in Books, Mountains, Statistics, Travel, University life with tags ABCDE, Adrian Raftery, applied statistics, Bayesian statistics, computational Bayesian methods, Environmental Statistics, Ireland, JSM 2024, Monte Carlo Statistical Methods, Oregon, Pacific North West, Paris 6, Portland, Seattle, statistical demography, United Nations, University of Washington, USA, UW, Washington State on July 28, 2024 by xi'an
reciprocal importance sampling
Posted in Books, pictures, Statistics with tags Adrian Raftery, ellipsoid, evidence, harmonic mean estimator, importance sampling, London, Paris, posterior density, reciprocal importance sampling, Thames on May 30, 2023 by xi'an
In a recent arXival, Metodiev et al. (including my friend Adrian Raftery, who is spending the academic year in Paris) proposed a new version of reciprocal importance sampling, expanding the proposal we made with Darren Wraith (2009) of using a Uniform over an HPD region. It is called THAMES, hence the picture (of London, not Paris!), for truncated harmonic mean estimator.
“…[Robert and Wraith (2009)] method has not yet been fully developed for realistic, higher-dimensional situations. For example, we know of no simple way to compute the volume of the convex hull of a set of points in higher dimensions.”
They suggest replacing the convex hull of the HPD points with an ellipsoid ϒ derived from a Normal distribution centred at the highest of the HPD points, whose covariance matrix is estimated from the whole (?) posterior sample. Which is somewhat surprising in that this ellipsoid may as well included low probability regions when the posterior is multimodal. For instance, the estimator is biased when the posterior cancels on parts of ϒ. And with an unclear fate for the finiteness of its variance, depending on how fast the posterior gets to zero on these parts.
The central feature of the paper is selecting the radius of the ellipse that minimises the variance of the (counter) evidence. Under asymptotic normality of the posterior. This radius roughly corresponds to our HPD region in that 50% of the sample stands within. The authors also notice that separate samples should be used to estimate the ellipse and to estimate the evidence. And that a correction is necessary when the posterior support is restricted. (Examples do not include multimodal targets, apparently.)
Model-Based Clustering, Classification, and Density Estimation Using mclust in R [not a book review]
Posted in Statistics with tags Adrian Raftery, book reviews, Chapman & Hall, classification, clustering, CRC Press, mclust, R, The R Series on May 29, 2023 by xi'an
Statistical Demography by Adrian Raftery [lectures]
Posted in Statistics, University life with tags Adrian Raftery, Fondation Sciences Mathématiques de Paris, FSMP, lecture, Seattle, statistical demography, Université de Paris, University of Washington on September 27, 2021 by xi'an
