A0439
Title: A flexible zero-inflated Poisson-Gamma model with application to microbiome sequence count data
Authors: Roulan Jiang - Tsinghua University (China)
Xiang Zhan - Peking University (China)
Tianying Wang - Colorado State University (United States) [presenting]
Abstract: In microbiome studies, it is of interest to use a sample from a population of microbes, such as the gut microbiota community, to estimate the population proportion of these taxa. However, due to biases introduced in sampling and preprocessing steps, these observed taxa abundances may not reflect true taxa abundance patterns in the ecosystem. Repeated measures, including longitudinal study designs, may be potential solutions to mitigate the discrepancy between observed abundances and true underlying abundances. Yet, widely observed zero-inflation and over-dispersion issues can distort downstream statistical analyses aiming to associate taxa abundances with covariates of interest. A Zero-Inflated Poisson Gamma (ZIPG) model framework is proposed to address these challenges above. From a perspective of measurement errors, the discrepancy between observations and truths is accommodated by decomposing the mean parameter in Poisson regression into a true abundance level and a multiplicative measurement of sampling variability is provided from the microbial ecosystem. A flexible ZIPG model framework by connecting both the mean abundance and the variability of abundances to different covariates and building valid statistical inference procedures for both parameter estimation and hypothesis testing. The proposed ZIPG method provides significant insights through comprehensive simulation studies and real data applications.
