Consider a linear model with n observations and k explanatory variables: (1)b $y=Xeta+u, usimN(0,sigma^2I_n)$. We assume that the model satisfies the ideal conditions. Consider the general linear constraints on regression coefficient vector: (2) $Reta=r$, where R and r are known matrices of orders $q imesk$ and q imes1$ respectively, and the rank of R is $q<k$. We also assume $n>k+q$.