Accession Number : AD0649679

Title :   IMPROVED ESTIMATION OF REGRESSION PARAMETERS.

Descriptive Note : Technical rept.,

Corporate Author : STANFORD UNIV CALIF DEPT OF STATISTICS

Personal Author(s) : Sclove,Stanley L.

Report Date : 25 JAN 1967

Pagination or Media Count : 21

Abstract : Correspondences between the problems of estimating the mean of a multivariate normal distribution and estimating regression parameters are presented and investigated to obtain minimax or admissible estimators of the regression parameters in normal multivariate (and univariate) regression models with respect to squared-distance loss functions. These new estimators are better than the maximum likelihood estimator, in that their risks are smaller, for all parameter values. (Author)

Descriptors :   (*REGRESSION ANALYSIS, PROBABILITY), MULTIVARIATE ANALYSIS, MINIMAX TECHNIQUE, FUNCTIONAL ANALYSIS

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE