Bootstrap Confidence Intervals for Reliability in 1-way ANOVA Random Model

  • Dal Ho Kim (Full-time Lecturer, Department of Statistics, Kyungpook National Unicersity, Taegu, 702-701, Korea) ;
  • Jang Sik Cho (Lecturer, Department of Statistics, Kyungpook National University, Taegu, 702-701, Korea)
  • 발행 : 1996.04.01

초록

We construct bootstrap confidence intervals for reliability, R= P{X>Y}, where X and Y are independent normal random variables. One way ANOVA random effect models are assumed for the populations of X and Y, where standard deviations $\sigma_{x}$ and $\sigma_{y}$ are unequal. We investigate the accuracy of the proposed bootstrap confidence intervals and classical confidence intervals work better than classical confidence interval for small sample and/or large value of R.

키워드

참고문헌

  1. IEEE v.40 no.5 Confidence Bounds for Pr(X>Y) in 1-Way ANOVA Random Model Aminzadeh, M. S.
  2. The Annals of Statistics v.7 Bootstrap Methods: Another Look at the Jackknife Efron, B.
  3. Canadian Journal of Statistics v.9 Nonparametric Standard Errors and Confidence Intervals (With Discussion) Efron, B.
  4. The Bootstrap and Other Resampling Plans The Jackknife Efron, B.
  5. Journal of the American Statistician Association v.82 Better Bootstrap Confidence intervals(With discussion) Efron, B.
  6. Technormetrics v.30 Confidence Limits for Stress-Strength Models with explanatory variables Guttman, I.;Johnshon, R.;Bhattacharyya, G. K.;Reisser, B.
  7. The Annals of Statistics v.16 Theoretical Comparison of Bootstrap Confidence Intervals (With Discussion) Hall, P.
  8. Technometrics v.28 Statistical Inference for Pr(Y
  9. Procedure of the third Berkeley Symposium Efficient nonparametric testing and estimation Stein, C.