Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 127 - Statistical Methods for Multi-Omic Data Analysis
Type: Topic-Contributed
Date/Time: Monday, August 9, 2021 : 1:30 PM to 3:20 PM
Sponsor: Section on Statistics in Genomics and Genetics
Abstract #317430
Title: Mixed-Effects Regression Models for Analyzing Data with Excess Zeros
Author(s): Yang Liu* and Guangyu Xu
Companies: Wright State University and Wright State University
Keywords: mixed-effects; excess zeros; association test

Data with excess zeros are common in multi-omic studies, such as in the RNA-sequencing data analysis. To investigate the association between a set of genetic variants and an outcome variable with excess zeros, two commonly used regression models are Hurdle models and zero-inflated models. In the talk, we propose a flexible framework to detect the mixed-effects in these two types of regression models. The proposed approach can test for both fixed effect and random effect for analyzing continuous or count outcome with excess zeros. Several efficient procedures have been proposed to combine the p-values of the test statistics for enhancing the statistical power. Simulation studies and a real omics data application demonstrate that the proposed method can significantly improve statistical power compared to competing methods, especially when the mixed effects are present in the analysis.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program