2021/06/28 by Martin Jankowiak, Jankowiak, Martin
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Bayesian Methods and Mixture Models #Computation (stat.CO) #FOS: Computer and information sciences #Machine Learning (stat.ML) #Metabolomics and Mass Spectrometry Studies #Methodology (stat.ME) #Statistical Methods and Bayesian Inference
paper · pdf · doi:10.48550/arxiv.2106.14981
openalex publication_date 2021/06/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Bayesian variable selection is a powerful tool for data analysis, as it\noffers a principled method for variable selection that accounts for prior\ninformation and uncertainty. However, wider adoption of Bayesian variable\nselection has been hampered by computational challenges, especially in\ndifficult regimes with a large number of covariates or non-conjugate\nlikelihoods. Generalized linear models for count data, which are prevalent in\nbiology, ecology, economics, and beyond, represent an important special case.\nHere we introduce an efficient MCMC scheme for variable selection in binomial\nand negative binomial regression that exploits Tempered Gibbs Sampling (Zanella\nand Roberts, 2019) and that includes logistic regression as a special case. In\nexperiments we demonstrate the effectiveness of our approach, including on\ncancer data with seventeen thousand covariates.\n