Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 248 - Recent Advances in Genetic Association and Gene-Environment Interaction Studies
Type: Contributed
Date/Time: Tuesday, August 9, 2022 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Genomics and Genetics
Abstract #322279
Title: Random-Effect Based Test for Multinomial Logistic Regression: Choice of the Reference Level and Its Impact on the Testing
Author(s): Qianchuan He and Yang Liu and Meiling Liu* and Michael C. Wu and Li Hsu
Companies: Fred Hutchinson Cancer Research Center and Wright State University and Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center
Keywords: genetic variants set ; invariance property; multinomial logistic regression; random effect score test; score statistics; statistical power
Abstract:

Random-effect score test has become an important tool for studying the association between a set of genetic variants and a disease outcome. While a number of random-effect score test approaches have been proposed in the literature, similar approaches for multinomial logistic regression have received less attention. In a recent effort to develop random-effect score test for multinomial logistic regression, we observed that such a test is not invariant to the choice of the reference level. In this talk, we will investigate why the multinomial logistic regression is not invariant to the reference level, and show how the choice of the reference level influences the power. Then we consider several potential procedures that are invariant to the reference level, and compare their performance through numerical studies.


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

Back to the full JSM 2022 program