Bootstrap Confidence Interval of Treatment Effect for Censored Data

  • Hyun Jong KIM (Department of Industrial Information Engineering, Kwang-ju University, Kwang-ju, 503-703, Korea) ;
  • Sang Gue PARK (Department of Applied Statistics, Chung-Ang University, Seoul, 156-756, Korea)
  • 발행 : 1997.12.01

초록

Consider the confidence interval estimators of treatment effect when some of data to be analyzed are randomly censored, assuming two-sample location-shift model. Recently proposed PARK and PARK(1995) Estimators is discussed and a bootstrap estimator is proposed. This estimator is compared with other well-known estimators throught the simulation studies and recommendations about the use are made.

키워드

참고문헌

  1. Statistica Neerlandica v.40 no.2 A distribution-free confidence interval for the difference between quantiles with censored data CHAKRABORTI, S.;DESU, M.M.
  2. Western Journal of Medicine v.126 Remission maintenance therapy in acute myelogenous leukemia EMBURY, S.H.;ELIAS, L.;HELLER, P.H.;HOOD, C.E.;GREENBERG, P.L.;SCHRIER, S.L.
  3. Counting Processes and survival Analysis FLEMING, T.R.;HARRINGTON, D.P.
  4. Biometrika v.52 A generalized Wilcoxon test for comparing arbitrary singly-censored samples GEHAN, E.
  5. Journal of the American Statistical Association v.53 Nonparametric estimation from incomplete observations KAPLAN, E.L.;MEIER, P.
  6. Journal of the Korean Statistical Society v.22 no.2 Two-sample inference for quantiles based on bootstrap for censored survival data KIM, J.
  7. Cancer Chemotheraphy Reports v.50 Evaluation of survival data and two new rank order statistics arising in its consideration MANTEL, N.
  8. Statistics and Probability Letters v.23 no.5 Quantile estimation of treatment effect for the two-sample problem with right censored data PARK, H.;PARK, S.
  9. Journal of the American Statistical Association v.85 no.410 Two-sample inference for median survival times based on one-sample procedures for censored survival data WANG, J.;HETTMANSPERGER, T.P.