Conditional Studentized survival tests for randomly censored models
The authors consider a two-sample problem for randomly right censored independent survival times. The \(H_0\) hypothesis is that these times are identically distributed in both samples. The test is based on the Studentized survival statistic. The authors derive a conditional central limit theorem (for fixed censoring status variables). The results are applied to the evaluation of the asymptotic test size. The derived asymptotics work even in the unbalanced sample size case when \(\min(n_1,n_2)\to\infty\), but not \(n_1/n_2\to\gamma\in(0,1)\) (\(n_i\) being the sizes of samples).
- Weighted logrank permutation tests for randomly right censored life science data
- Weighted resampling of martingale difference arrays with applications
- Bootstrap and permutation rank tests for proportional hazards under right censoring
- Wild bootstrap logrank tests with broader power functions for testing superiority
- A Monte-Carlo comparison of Studentized bootstrap and permutation tests for heteroscedastic two-sample problems
- Resampling Student's \(t\)-type statistics
- Randomized empirical processes by algebraic groups, and tests for weak null hypotheses
- Permutation tests from biased samples for the equality of two distributions
- scientific article; zbMATH DE number 1058154 (Why is no real title available?)
- More powerful logrank permutation tests for two-sample survival data
- CASANOVA: Permutation inference in factorial survival designs
This page was built for publication: Conditional Studentized survival tests for randomly censored models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2739865)