Discrete time hazards models for occupational and environmental cohort analyses.

Abstract

To discuss the use of discrete time hazards models for the analysis of occupational and environmental cohort data. Analytical data structures and regression methods for discrete time hazards models are described. This approach is illustrated via analyses of data from a study of mortality in a cohort of chemical workers exposed to dioxin. Analyses employing a discrete time hazards model facilitate examination of observed and expected counts, the calculation of attributable fractions, and empirical description of the estimated hazard rates. In addition, this approach can be used to fit non-multiplicative models, such as the linear hazards ratio model (which has been employed in epidemiological analyses of a variety of environmental and occupational exposures).