Likelihood Ratio Test for Detecting Gene (G)- Environment (E) Interactions Under Additive Risk Models Exploiting G-E Independence for Case-Control Studies

• Activity Number: 357
• Type: Contributed
• Date/Time: Tuesday, August 2, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Summer S. Han*+ and Philip S. Rosenberg and Nilanjan Chatterjee
• Companies: National Cancer Institute and National Cancer Institute and National Cancer Institute
• Keywords: GxE interaction ; Additive risk model ; multiplicative risk model ; case-control study ; gene-environment independence

Abstract

There has been a long-standing controversy in epidemiology on deciding an appropriate risk scale for testing interactions between gene (G) and environmental exposure (E). Although interaction tests based on multiplicative risk models have been more widely applied due to its convenience in statistical modeling, interactions under additive risk models have been regarded to be closer to true biological interactions and considered to be more useful in intervention-related decision making processes in public health. It's well known that exploiting the independence information between G and E increases the power of interaction tests. Such approaches, however, have been limitedly applied to the multiplicative scale interaction tests. In this article, we propose a likelihood ratio test for detecting additive scale interactions for case-control studies that incorporates the G-E independence information. Simulation study was conducted to compare the performances of our approach and traditional methods including synergy index (SI), which do not take into account the independence information. We illustrate our method by application to National Cancer Institute lung cancer and smoking data.