A Note on Admissibility and Finite Admissibility in Estimation

  • Byung Hwee Kim (Department of Mathematics, Hanyang University, Seoul, 133-791, KOREA) ;
  • Tae Ryoung Park (Department of Applied Mathematics, Seokyeong University, Seoul, 136-704, KOREA)
  • 발행 : 1994.12.01

초록

Consider the problem of estimating the parameter of the model in which an observable random variable is represented by a unknown scalar parameter plus another random variable and the parameter, sample, and decision spaces consist of all integers. We first characterize the class of all admissible estimators and then characterize the class of all finitely admissible estimators. Finally, we show that two classes are identical.

키워드

참고문헌

  1. Sankhya Ser. B v.45 no.Ser. B Estimation of the variance in finite population sampling Ghosh, M.;Meeden, G.
  2. The annals of Statistics v.7 no.4 A stepwise Bayesian procedure Hsuan, F. C.
  3. Journal of the Korean Statistical Society v.16 no.2 Admissibility of some stepwise Bayes estimators Kim, B. H.
  4. Sankhya Ser. A v.51 The admissibility of the maximum likelihood estimator for estimating a transition matrix Meeden, G.
  5. Proceedings of the Golden Jubilee Conference of the Indian Statistical Institute On the admissibility and uniform admissibility of ratio type estimators Meeden, G.;Ghosh, M.
  6. The Annals of Statistics v.11 no.1 Choosing between experiments : Applications to finite population smapling Meeden, G.;Ghosh, M.
  7. The Annals of Statistics v.17 no.4 The admissibility of the Kaplan-Meier and other maximum likelihood estimators in the presence of censoring Meeden, G.;Ghosh, M.;Srinivasan, C.;Vardeman, S.
  8. The Annals of Statistics v.12 no.2 Admissible estimators for the total of a stratified population that employ prior information Vardeman, S.;Meeden, G.