A Simulation Study of the Effect of Study Duration on Modeling Environmental Risk of Cancer

• Activity Number: 603
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 2:00 PM to 3:50 PM
• Sponsor: ENAR
• Author(s): Kevin Donges*+ and Catherine A. Calder and David Wheeler
• Companies: The Ohio State University and Ohio State University and Virginia Commonwealth University
• Keywords: Environment ; Cancer ; Simulation

Abstract

Exposure to certain environmental toxins is thought to increase risk of developing many types of cancer (e.g., bladder cancer.) However, the effect of past exposures is often difficult to quantify due to the long induction period of some types of cancer and the increased measurement error in exposure which results from residential mobility. In response, case-control studies that account for residential history are increasingly being conducted. While traditional methods of analysis employ a cumulative measure of exposure in a logistic regression model, a recently proposed approach treats the case-control study as a cohort study and exposure as a time-dependent covariate in a Cox proportional hazards model. However, it is unknown what impact the relatively short study enrollment periods often employed in case-control studies have on the gains in model validity when using the survival analysis approach. In an effort to assess the impact of the length of the study enrollment period in modeling the effect of environmental exposures on the risk of developing cancer, we present a simulation study that compares the performance of the logistic regression and Cox proportional hazards models.