Stein's positive part estimator and bayes estimator
Stein's positive part estimator forp normal means is known to dominate the M.L.E. ifp≧3. In this article by introducing some proirs we show that Stein's positive part estimator is posterior mode. We also consider the Bayes estimators (posterior mean) with respect to the same priors and show that some of them dominate M.L.E. and are admissible.
KeywordsStein Multivariate Normal Distribution Balance Incomplete Block Design Posterior Mode Quadratic Loss Function
Unable to display preview. Download preview PDF.
- National Bureau of Standards, Applied Mathematics Series 55 (1964).Handbook of Mathematical Functions with Formulas, Graphs and Mathematical Tables.Google Scholar
- Stein, C. M. (1966). An approach to the recovery of inter-block information in balanced incomplete block designs, In Festschrift for J. Neyman:Research Papers in Statistics (ed. F. N. David), Wiley, New York, 351–366.Google Scholar