Write a script/function file on matlab with its first line as function A = correlatedVariables(m,n,C,Mu) where m is the number of rows of matrix A and n is the number of columns of A. Mu is the mean vector, and C is the covariance matrix. So when you type in the command window of matlab a mean vector Mu and a covariance matrix C, and use this function file that lets you use different m and n values, it gives you a matrix A whose mean and covariance is apporoximately the same as the ones we entered in the command window.