{"id":660,"date":"2017-09-28T08:29:32","date_gmt":"2017-09-28T08:29:32","guid":{"rendered":"http:\/\/jsr.isrt.ac.bd\/?post_type=article&p=660"},"modified":"2017-09-28T08:30:18","modified_gmt":"2017-09-28T08:30:18","slug":"estimation-parameters-simple-multivariate-linear-model-student-t-errors","status":"publish","type":"article","link":"http:\/\/jsr.isrt.ac.bd\/article\/estimation-parameters-simple-multivariate-linear-model-student-t-errors\/","title":{"rendered":"Estimation of parameters of the simple multivariate linear model with student t-errors"},"content":{"rendered":"
This paper considers estimation of the intercept and slope vector parameters of
\nthe simple multivariate linear regression model with Student-t errors in the presence
\nof uncertain prior information on the value of the unknown slope vector. The
\nunrestricted, restricted, preliminary test, shrinkage, and positive-rule shrinkage
\nestimators are defined together with the expressions for the bias, quadratic bias,
\nquadratic risk and mean squared errors (mse) functions of the estimators are derived.
\nComparison of the estimators is made using quadratic risk criterion. Based
\non the study we conclude that for shrinkage estimators are recommended,
\nand for , the preliminary test estimators are preferable.<\/p>\n