New Shrinkage Estimation in t-Regression Model with StochasticSub-Space Restriction

This paper intruduces a new biased shrinkage estimator for estimation of regression coeficients in the multivariate-t linear model with stochastic restrictions. Its bias and quadratic risk functions are derived approximately. It is evident from the numerical results that the shrinkage estimator outperforms the generalized least squares estimator in risk since.