GENERALIZED BAYES STEIN-TYPE ESTIMATORS FOR REGRESSION PARAMETERS UNDER LINEAR CONSTRAINTS

The problem of estimating the k-dimensional parameter vector in a linear regression model with m linear restrictions is considered. The proposed estimators are generalized Bayes with respect to a prior distribution compatible with the linear restrictions. Under certain conditions some of the generalized Bayes estimators dominate the ordinary least-squares estimator and are admissible. © 1993 Academic Press Inc.