IIUM Repository

K-sample tests based on survival analysis with interval-censored data

Elfaki, Faiz Ahmed Mohamed and Daud, Isa and Noor Akma, Ibrahim and Jamal Ibrahim, Daoud and Usman, Mustofa and Lukman, Iing (2009) K-sample tests based on survival analysis with interval-censored data. International Journal of Science Engineering and Technology, 2 (1). pp. 19-25. ISSN 1985-3785

[img] PDF (K-sample tests) - Published Version
Restricted to Repository staff only

Download (4MB) | Request a copy

Abstract

The nonparametric tests are introduced and provides a new method to compare survival functions among groups when the data are interval-censored. The k-sample test for interval censored is studied. Many k-sample tests have been developed when data are uncensored or right censored. The main characteristic of this paper is the permutational distributions of survival analysis with interval-censored data The difficulty of finding the distribution of the test statistic is avoided with this permutational approach. The permutational methodology will be introduced and provides description of the permutational Wilcoxon and Log-rank tests for interval-censored data. A likelihood approach for this new proposal is also considered. The relationship given by Fay (1999) betWeen permutational methods and likelihood methods based on score test statistics will be extended. It was found that the permutational approach requires that the censoring mechanisms are identical across the groups.

Item Type: Article (Journal)
Additional Information: 4925/6271
Uncontrolled Keywords: K-sample test; Censored data; Survival data; Permutational; EM algorithm
Subjects: Q Science > QA Mathematics
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): Kulliyyah of Engineering > Department of Science
Depositing User: Assoc.Prof.Dr Jamal Daoud
Date Deposited: 10 Nov 2011 16:51
Last Modified: 21 Nov 2011 22:53
URI: http://irep.iium.edu.my/id/eprint/6271

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year