Premium
Omnibus Two‐Sample Test Procedures with Randomly Censored Data
Author(s) -
Koziol J. A.,
Yuh Y. S.
Publication year - 1982
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710240804
Subject(s) - statistics , censorship , statistical hypothesis testing , sample (material) , mathematics , probability and statistics , subject (documents) , computer science , physics , library science , law , thermodynamics , political science
Versions of the K OLMOGOROV ‐S MIRNOV , K UIPER , and c RAMéR ‐V ON M ISES statistics are introduced for the problem of comparing the underlying survival distributions of two populations when observations are subject to random censorship, and a two‐sided alternative is of interest. These statistics are shown to have readily amenable asymptotic distributions; furthermore, the statistics reduce to their classical counterparts in the absence of censorship. Data pertaining to a cancer chemotherapy experiment are examined with these statistics.