Nonparametric Tests for the Gap Time Distributions of Serial Events Based on Censored Data

• Published in: Biometrics Vol. 57; no. 2; pp. 369 - 375
• Main Authors: Lin, D. Y., Ying, Zhiliang
• Format: Journal Article
• Language: English
• Published: Oxford, UK Blackwell Publishing Ltd 01.06.2001; International Biometric Society
• Subjects: Asymptotic properties; Biometrics; biometry; Censored data; Censorship; Chemotherapy, Adjuvant; clinical trials; Colonic Neoplasms - drug therapy; Colonic Neoplasms - mortality; Colonic Neoplasms - surgery; Colorectal cancer; colorectal neoplasms; Consistent estimators; Correlated failure times; Dependent censoring; Estimators; Humans; Kaplan Meier estimator; Log-rank statistic; Models, Statistical; Multiple events; Nonparametric tests; Randomized Controlled Trials as Topic; Recurrence; Recurrent events; Reproducibility of Results; Statistical variance; statistics; Statistics, Nonparametric; Survival analysis; Survival Rate; Time Factors
• ISSN: 0006-341X; 1541-0420
• DOI: 10.1111/j.0006-341X.2001.00369.x

This article deals with the problem of comparing two populations with respect to the distribution of the gap time between two successive events when each subject can experience a series of events and when the event times are potentially right censored. Several families of nonparametric tests are developed, all of which allow arbitrary distributions and dependence structures for the serial events. The asymptotic and small‐sample properties of the proposed tests are investigated. An illustration with data taken from a colon cancer study is provided. The related problem of testing the independence of two successive gap times is also studied.