A MONTE-CARLO STUDY OF TIME AGGREGATION IN CONTINUOUS-TIME AND DISCRETE-TIME PARAMETRIC HAZARD MODELS

This study investigates the effects of time aggregation in discrete an d continuous-time hazard models. A Monte Carlo study is conducted in w hich data are generated according to various continuous and discrete-t ime processes, and aggregated into daily, weekly and monthly intervals . These data are analyzed with flexible continuous-time and discrete-t ime parametric hazard models. The estimates of the structural paramete r and baseline hazard seem robust to the form of the distribution of t he data generation process when the time-aggregation window is small. Both estimates of continuous-time models and of discrete-time models s uffer from time aggregation, but the estimates of the discrete-time mo del are more sensitive to aggregation. (C) 1998 Elsevier Science S.A.