i dont understand how to get the function from which you can calculate the fisher information matrix from the multinormal distribution.

The joint pdf is a function of X1,X2,....Xn r.v and p1,p2,....,pk parameters whilst the function to calculate the information matrix is of a single X variable r.v.

Do i just take the marginal distribution of the mulitnormal, this results in the binomial distribution with just two parameters though ???? confused