Summary
Estimation-preceded-by-testing is studied in the context of estimating the mean vector of a multivariate normal distribution under squared error loss together with a complexity cost. It is shown that although the preliminary test estimator is admissible for the univariate problem (cf Meeden and Arnold (1979),J. Amer. Statist. Assoc.,74, 872–874), for dimensionp≧3, the estimator is inadmissible. A new preliminary test estimator is obtained, which depends on the cost for each component and dominates the usual preliminary test estimator.
Similar content being viewed by others
References
Baranchik, A. J. (1970). A family of minimax estimators of the mean of a multivariate normal distribution,Ann. Math. Statist.,41, 642–645.
Bock, M. E., Yancey T. A. and Judge, G. G. (1972). The statistical consequences of preliminary test estimators in regression,J. Amer. Statist. Assoc.,68, 109–116.
Brown, L. D. and Hwang, J. T. (1982). A unified admissibility proof. Statistical Decision Theory and Related Topics III, Academic Press, (eds. S. S. Gupta and J. Berger), Vol. I, 205–230.
Faden, A. M. and Rausser, G. C. (1976). Econometric policy model construction: the post-Bayesian approach,Ann. Economic and Social Measurement,5, 349–362.
Meeden, G. and Arnold, B. C. (1979). The admissibility of a preliminary test estimator when the loss incorporates a complexity cost,J. Amer. Statist. Assoc.,74, 872–874.
Nagata, Y. (1983). Admissibility of some preliminary test estimators for the mean of normal distribution,Ann. Inst. Statist. Math. 35, 365–373.
Sclove, S. L., Morris, C. and Radhakrishnan, R. (1972). Non optimality of preliminary-test estimators for the mean of a multivariate normal distribution,Ann. Math. Statist.,43, 1481–1490.
Stein, C. (1981). Estimation of the mean of a multivariate normal distribution,Ann. Statist.,9, 1135–1151.
Strawderman, W. E. (1971). Proper Bayes minimax estimators of the multivariate normal mean,Ann. Math. Statist.,42, 385–388.
Author information
Authors and Affiliations
Additional information
Research partially supported by the NSF Grant Number DMS-82-18091 and partially by the DSR Research Development Award, University of Florida.
About this article
Cite this article
Ghosh, M., Dey, D.K. On the inadmissibility of preliminary-test estimators when the loss involves a complexity cost. Ann Inst Stat Math 38, 419–427 (1986). https://doi.org/10.1007/BF02482528
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02482528