Bayesian Variable Selection for Random Intercept Modeling of Gaussian and Non推荐.pdfVIP

Bayesian Variable Selection for Random Intercept Modeling of Gaussian and Non‐ Gaussian Data University Press Scholarship Online Oxford Scholarship Online Bayesian Statistics 9 José M. Bernardo, M. J. Bayarri, James O. Berger, A. P. Dawid, David Heckerman, Adrian F. M. Smith, and Mike West Print publication date: 2011 Print ISBN-13: 9780199694587 Published to Oxford Scholarship Online: January 2012 DOI: 10.1093/acprof:oso/9780199694587.001.0001 Bayesian Variable Selection for Random Intercept Modeling of Gaussian and Non‐Gaussian Data Sylvia Frühwirth‐Schnatter Helga Wagner DOI:10.1093/acprof:oso/9780199694587.003.0006 Abstract and Keywords The paper demonstrates that Bayesian variable selection for random intercept models i closely related to the appropriate choice of the distribution of heterogeneity. If, for instance, a Laplace rather than a normal prior is considered, we obtain a Bayesian La o random effects model which allows both smoothing and, additionally, individual shrinkage of the random effects toward 0. In addition, we study spike‐and‐slab random effect models with both an absolutely continuous and a Dirac spike and provide details of MCMC estimation for all models. Simulation studies comparing the various priors show that the spike‐and‐slab random effects model outperforms unimodal, non‐Gau ian prior as far as correct cla ification of non‐zero random effects is concerned and that there i surprisingly little difference between an absolutely continuous and a Dirac spike. The Page 1 of 43 Bayesian Variable Selection for Random Intercept Modeling of Gaussian and Non‐ Gaussian Data choice of appropriate component densities, however, is crucial and we were not able to identify a uniformly best distribution family. The paper concludes with an application to ANOVA for binomial data using a logit model with a random intercept. Keywords: Bayesian Lasso, M