Controlling for Birth Cohort Effects in the Age-Based Cox Proportional Hazards Model

• Activity Number: 257
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Misty Jena Hein*+ and Mary Schubauer-Berigan and James Deddens
• Companies: CDC/NIOSH and CDC/NIOSH and CDC/NIOSH/University of Cincinnati
• Keywords: Epidemiologic methods ; Cox proportional hazards models ; Cohort studies ; Nested case-control studies

Abstract

The nested case-control design is frequently used to evaluate exposures and health outcomes within the confines of a cohort study. When incidence density sampling (IDS) is used to identify controls, the resulting data can be analyzed using conditional logistic regression (equivalent to stratified Cox proportional hazards regression). In these studies, exposure lagging is used to account for disease latency. In light of recent criticism of IDS, we used simulated cohorts to evaluate age-based IDS for lagged exposures in the presence of birth cohort effects and associations among time-related variables. Effect estimates were unbiased when adjusted for birth cohort; however unadjusted effect estimates were biased, particularly when hire age and year were correlated. When adjusted for birth cohort, including lagged-out cases and controls (assigned zero lagged exposure) did not introduce bias.