This post has NOT been accepted by the mailing list yet.
I am trying to write a code for maximum likelihood estimation of multivariate model with normal error terms.
y = x*b + u
Here, say y is a bivariate vector and u has a multivariate normal distribution. x are regressors and b is the parameter vector. How can I code this by using ML command? One outstanding problem is that I don't know how to model the variance covariance matrix of u. Any way to write the log likelihood and make the ML estimation? Thanks!