Abstract: In this paper,the mixed estimations of regression coefficient in multivariate linear model is given on the condition of expanding sample data and their optimalities are considered. It is shown that GLSE is equivalent to the above mentioned mixed estimations.Furthermore, Bayes estimation in multivariate normal model,which is the same as the mixed estimations,is also  improved.

Key words: multivariate linear model, mixed estimation, Bayes estimation, expanding sample data