演講公告 90年11月26日 (星期一)

摘要

Recurrent event data are largely characterized by the rate function but smoothing techniques for estimating the rate function have never been rigorously developed or studied in statistical literature. In this talk, I'll introduce the moment and least squares methods for estimating the rate function from recurrent event data. With an independent censoring assumption on the recurrent event process, we develop smoothing estimation procedures and study statistical properties of the proposed estimators. Bootstrap methods are proposed to establish the criteria for bandwidth selection and construct the approximated confidence intervals for the rate function. In general, the moment method approach produces curves with nicks occurring at the censoring times, whereas the least squares method can avoid this problem. Also, the asymptotic variance of the least squares estimator is shown to be smaller under regularity conditions. However, in the implementation of the bootstrap procedures, the moment method is computationally more efficient than the least squares method because the former approach uses condensed bootstrap data. The performance of the proposed procedures are studied through Monte Carlo simulations and an epidemiological example on intravenous drug users.