ABSTRACT
We define these concepts in details dealing with the multivariate normal distribution though they apply to other multivariate distributions defined above.
We observed in Theorem 4.1.5 that the conditional probability density function of X(2) given that X(1)=x(1), is a (p-q)-variate normal with mean and covariance matrix
The matrix is called the matrix of regression coefficients of X(2) on X(1)=x(1).
