On maximum likelihood estimation in factor analysis-An algebraic derivation

The maximum likelihood estimate in factor analysis is typically obtained as the solution of the stationary point equation of the likelihood function. This type of derivation suffers from two problems: it is rather cumbersome and, in fact, it is incomplete as it does not include a proof that the so-obtained estimate is indeed a global maximum point of the likelihood function. In this note we present a simple algebraic derivation of the maximum likelihood estimate in factor models with spherical noise that applies to the general complex-valued data case. (C) 2009 Elsevier B.V. All rights reserved.