Summary
In this paper we investigate Empirical Bayes Estimators (EBE) in a misspecified linear regression model. Comparisons are made between the EBE and the Ordinary Least Squares Estimator (OLSE) in terms of the Matrix Mean Square Error Criterion (MMSE). Conditions are derived under which the EBE is better than OLSE. Finally we examine the superiority of the EBE-based predictor over the OLSE-predictor.
Similar content being viewed by others
References
Arnold, S. F. (1981).The Theory of Linear Model and Multivariate Analysis. New York: Wiley.
Berger, T. O. (1985).Statistical Decision Theory and Bayesian Analysis. Berlin: Springer.
Clemmer, B. A. and Krutchkoff, R. G. (1968). The use of empirical Bayes estimator in a linear regression model.Biometrika 55, 525–534.
Efron, B. and Morris, C. (1972) Empirical Bayes on vector observation: An extension of Stein’s method.Biometrika 59, 335–347.
Efron, B. and Morris, C. (1973). Stein’s estimation rule and it’s competitors—An empirical Bayes approach.J. Amer. Statist. Assoc. 68, 117–130.
Ghosh, M., Saleh, A. K. Md. E. and Sen, P. K. (1989). Empirical Bayes subset estimation in regression model.Statistics and Decisions 7, 15–35.
Kadiyala, K. (1986). Mixed regression estimator under misspecification.Economics Letters 21, 21–30.
Singh, R. S. (1985). Empirical Bayes estimation in a multiple linear regression model.Ann. Inst. Statist. Math. 37, part A, 71–86.
Zacks, S. (1981).Parametric Statistical Inference. New York: Pergamon Press.
Author information
Authors and Affiliations
Additional information
An erratum to this article is available at http://dx.doi.org/10.1007/BF02562691.
Rights and permissions
About this article
Cite this article
Wei, L., Trenkler, G. Mean square error matrix superiority of Empirical Bayes Estimators under misspecification. Test 4, 187–205 (1995). https://doi.org/10.1007/BF02563109
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02563109