Open Access
Translator Disclaimer
June 2020 Bayesian Sparse Multivariate Regression with Asymmetric Nonlocal Priors for Microbiome Data Analysis
Kurtis Shuler, Marilou Sison-Mangus, Juhee Lee
Bayesian Anal. 15(2): 559-578 (June 2020). DOI: 10.1214/19-BA1164


We propose a Bayesian sparse multivariate regression method to model the relationship between microbe abundance and environmental factors for microbiome data. We model abundance counts of operational taxonomic units (OTUs) with a negative binomial distribution and relate covariates to the counts through regression. Extending conventional nonlocal priors, we construct asymmetric nonlocal priors for regression coefficients to efficiently identify relevant covariates and their effect directions. We build a hierarchical model to facilitate pooling of information across OTUs that produces parsimonious results with improved accuracy. We present simulation studies that compare variable selection performance under the proposed model to those under Bayesian sparse regression models with asymmetric and symmetric local priors and two frequentist models. The simulations show the proposed model identifies important covariates and yields coefficient estimates with favorable accuracy compared with the alternatives. The proposed model is applied to analyze an ocean microbiome dataset collected over time to study the association of harmful algal bloom conditions with microbial communities.


Download Citation

Kurtis Shuler. Marilou Sison-Mangus. Juhee Lee. "Bayesian Sparse Multivariate Regression with Asymmetric Nonlocal Priors for Microbiome Data Analysis." Bayesian Anal. 15 (2) 559 - 578, June 2020.


Published: June 2020
First available in Project Euclid: 19 June 2019

MathSciNet: MR4078725
Digital Object Identifier: 10.1214/19-BA1164

Keywords: count data , harmful algal bloom , microbiome , negative binomial , next-generation sequencing , nonlocal prior , stochastic search variable selection


Vol.15 • No. 2 • June 2020
Back to Top