Two-sample chi-square test for randomly censored data

임의로 관측중단된 두 표본 자료에 대한 카이제곱 검정방법

  • 김주한 ((305-764) 대전직할시 유성구 궁동 220번지, 충남대학교 자연과학대학 통계학과) ;
  • 김정란 ((305-764) 대전직할시 유성구 궁동 220번지, 충남대학교 자연과학대학 통계학과)
  • Published : 1995.09.01

Abstract

A two sample chi-square test is introduced for testing the equality of the distributions of two populations when observations are subject to random censorship. The statistic is appropriate in testing problems where a two-sided alternative is of interest. Under the null hypothesis, the asymptotic distribution of the statistic is a chi-square distribution. We obtain two types of chi-square statistics ; one as a nonnegative definite quadratic form in difference of observed cell probabilities based on the product-limit estimators, the other one as a summation form. Data pertaining to a cancer chemotheray experiment are examined with these statistics.

Keywords

References

  1. Annals of Statististics v.2 A large sample study of the life table and product limit estimates under random censorship Breslow,N.;Crowley,J.
  2. Proceedings of 5th Berkeley Symposium v.5 The two sample problem with censored data Efron,B.
  3. Biometrika v.52 A generalized Wilcoxen test for comparing arbitrarily single censored samples Gehan,E.A.
  4. Annals of Statististics v.11 Larger sample behavior of the product-limit estimator on the whole line Gill,R.
  5. Journal of the American Statistical Association v.53 Nonparametric estimation from incomplete obser-vations Kaplan,E.L.;Meier,P.
  6. Annals of Statististics v.21 Chi-square goodness-of-fit tests for randomly censored data Kim,J.H.
  7. Biometrical Journal v.20 A two-sample Cramer-von Mises test for randomly censored data Koziol,J.
  8. Biometrical Journal v.24 Omnibus two-sample test procedures with randomly censored data Koziol,J.;Yuh,Y.S.
  9. Cancer Chemotherapy Reports v.50 Evaluation of survival data and two new rank statistics arising in its consideration Mantel,N.
  10. Journal of the Royal Statistical Society, Series A v.135 Asymptotically efficient rank invariant test procedures(with discussion) Peto,R.;Peto,J.