| Summary: | 碩士 === 國立臺灣大學 === 流行病學研究所 === 93 === Repeated events data are encountered in many longitudinal studies such as computer breakdowns and motorcycle crashes that can occur repeatedly.over time for each subject. Truncated repeated events data often arises when subjects experience a certain event prior to study. Most statistical methods for the truncated repeated events data depend on the assumption of quasi-independence that repeated event times and truncation time are independent in the observable region. However, in many applications, this assumption might be unrealistic. In this article, we propose a nonparametric test statistic to test the quasi-independence assumption for truncated repeated event data in the presence of right censoring, which is an extension of the conditional Kendall’s tau. Simulation studies are conducted to investigate the performance of the proposed test statistic. A real example is also presented to illustrate the proposed test.
|
|---|
