Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지

Comparison of Best Invariant Estimators with Best Unbiased Estimators in Location-scale Families

  • Published : 1999.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

In order to estimate a parameter $(\alpha,\beta^r), r\epsilonN$, in a distribution belonging to a location-scale family we usually use best invariant estimator (BIE) and best unbiased estimator (BUE). But in some conditions Ryu (1996) showed that BIE is better than BUE. In this paper we calculate risks of BIE and BUE in a normal and an exponential distribution respectively and calculate a percentage risk improvement exponential distribution respectively and calculate a percentage risk improvement (PRI). We find the sample size n which make no significant differences between BIE and BUE in a normal distribution. And we show that BIE is always significantly better than BUE in an exponential distribution. Also simulation in a normal distribution is given to convince us of our result.

Keywords

References

  1. Ann. Math. Statist. v.25 Some theorems relevant to life testing from an exponential distribution Epstein, B.;Sobel, M.
  2. Theory of Point Estimation Lehmann, E.L.
  3. Biometrika v.30 The estimation of the location and scale parameters of a continuous population of any given form Pitman, E.J.G.
  4. Journal of Statistical Planning and Inference v.40 Simultaneous equivariant estimation for location-scale models Prabakaran, T.E.;Chandrasekar, B.
  5. A study on the invariance principle and its applications in statistical inference Ryu, S.K.
  6. The Annals of Statistics v.9 Relation of the best invariant predictor and the best unbiased predictor in location and scale families Takada, Y.