19197 6 103588 2 315822 document 103588 Ultimate P lya Gamma Samplers Efficient MCMC for Possibly Imbalanced Binary and Categorical Data.pdf application/pdf e7ceb2143d449aab3b65a2e45e2704b9 MD5 2387956 2023-11-20 15:14:42 https://pure.iiasa.ac.at/id/eprint/19197/1/Ultimate%20P%20lya%20Gamma%20Samplers%20Efficient%20MCMC%20for%20Possibly%20Imbalanced%20Binary%20and%20Categorical%20Data.pdf 19197 1 1 application/pdf text en public cc_by_nc_nd_4

Ultimate P lya Gamma Samplers Efficient MCMC for Possibly Imbalanced Binary and Categorical Data.pdf

published 103590 1 315835 document 103590 indexcodes.txt text/x-c 3c3afb8e4e35869e092f6e35d306b477 MD5 10676 2023-11-20 15:24:16 https://pure.iiasa.ac.at/id/eprint/19197/2/indexcodes.txt 19197 2 2 text/x-c other Generate index codes conversion from text to indexcodes en public

indexcodes.txt

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/isIndexCodesVersionOf https://pure.iiasa.ac.at/id/document/103588 103591 2 315836 document 103591 lightbox.jpg image/png 70cacc14306cfe6f90fa5dc26f03d639 MD5 27761 2023-11-20 15:24:44 https://pure.iiasa.ac.at/id/eprint/19197/3/lightbox.jpg 19197 3 3 image/png other Thumbnails conversion from text to thumbnail_lightbox en public

lightbox.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/islightboxThumbnailVersionOf https://pure.iiasa.ac.at/id/document/103588 103592 2 315837 document 103592 preview.jpg image/png d394629b024f11407a3e5a36c9a83093 MD5 12746 2023-11-20 15:24:45 https://pure.iiasa.ac.at/id/eprint/19197/4/preview.jpg 19197 4 4 image/png other Thumbnails conversion from text to thumbnail_preview en public

preview.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/ispreviewThumbnailVersionOf https://pure.iiasa.ac.at/id/document/103588 103593 2 315838 document 103593 medium.jpg image/png c78d6bdf68ac0d0094e6ff4a78b45f1c MD5 4562 2023-11-20 15:24:45 https://pure.iiasa.ac.at/id/eprint/19197/5/medium.jpg 19197 5 5 image/png other Thumbnails conversion from text to thumbnail_medium en public

medium.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/ismediumThumbnailVersionOf https://pure.iiasa.ac.at/id/document/103588 103594 2 315839 document 103594 small.jpg image/png 86a17a1d59f5d3e24ee57072c20b07dd MD5 1535 2023-11-20 15:24:46 https://pure.iiasa.ac.at/id/eprint/19197/6/small.jpg 19197 6 6 image/png other Thumbnails conversion from text to thumbnail_small en public

small.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/103588 http://eprints.org/relation/issmallThumbnailVersionOf https://pure.iiasa.ac.at/id/document/103588 archive 353 disk0/00/01/91/97 2023-11-20 15:17:13 2023-11-20 15:17:13 2023-11-20 15:17:13 article show Zens G. 2431 Frühwirth-Schnatter S. Wagner H. pub POPJUS MIG Bayesian; Data augmentation; Gibbs sampling; MCMC boosting; Parameter expansion Modeling binary and categorical data is one of the most commonly encountered tasks of applied statisticians and econometricians. While Bayesian methods in this context have been available for decades now, they often require a high level of familiarity with Bayesian statistics or suffer from issues such as low sampling efficiency. To contribute to the accessibility of Bayesian models for binary and categorical data, we introduce novel latent variable representations based on Pólya-Gamma random variables for a range of commonly encountered logistic regression models. From these latent variable representations, new Gibbs sampling algorithms for binary, binomial, and multinomial logit models are derived. All models allow for a conditionally Gaussian likelihood representation, rendering extensions to more complex modeling frameworks such as state space models straightforward. However, sampling efficiency may still be an issue in these data augmentation based estimation frameworks. To counteract this, novel marginal data augmentation strategies are developed and discussed in detail. The merits of our approach are illustrated through extensive simulations and real data applications. Supplementary materials for this article are available online. 2023-09-20 published Taylor & Francis doi:10.1080/01621459.2023.2259030 3663 public Journal of the American Statistical Association 1-12 TRUE 0162-1459 no info:eu-repo/semantics/article