Maximum-likelihood estimation of the parameters of a multivariate normal distribution (Q1071428)

The authors provide an exposition of alternative approaches for obtaining maximum-likelihood estimators (MLE) for the parameters of a multivariate normal distribution under different assumptions about the parameters. Matrix differentiation and matrix transformations are the general techniques on which the authors have given a central focus. These are systematically applied to derive the MLE of the means under a rank constraint and of the covariances when there are missing observations. Derivations using induction and inequalities are also included to exhibit alternative methods. The connection with an econometric model is also presented.