Abstract
Peto and Peto (1972) have studied rank invariant tests to compare two survival curves for right censored data. We apply their tests, including the logrank test and the generalized Wilcoxon test, to left truncated and interval censored data. The significance levels of the tests are approximated by Monte Carlo permutation tests. Simulation studies are conducted to show their size and power under different distributional differences. In particular, the logrank test works well under the Cox proportional hazards alternatives, as for the usual right censored data. The methods are illustrated by the analysis of the Massachusetts Health Care Panel Study dataset.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 163-174 |
| Number of pages | 12 |
| Journal | Journal of Statistical Computation and Simulation |
| Volume | 61 |
| Issue number | 1-2 |
| DOIs | |
| State | Published - 1998 |
Bibliographical note
Funding Information:The author would like to thank his thesis advisor Rick Chappell for guidance and discussions. Zhengqing Li helped to raise the author's attension to this problem. The author is also grateful to the referee and the Associate Editor for insightful comments which led to an improved presentation. This research was supported by Grant EY10769-01 from the National Eye Institute.
Keywords
- Logrank test
- Monte Carlo permutation test
- Nonparametric maximum likelihood estimator (NPMLE)
- Smoothed nonparametric estimator (SNE)
- Wilcoxon test
Fingerprint
Dive into the research topics of 'Rank invariant tests with left truncated and interval censored data'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS