PSEUDO-MAXIMUM LIKELIHOOD METHOD, ADJUSTED PSEUDO-MAXIMUM LIKELIHOOD METHOD AND COVARIANCE ESTIMATORS

In this paper, we introduce an adjusted pseudo-maximum likelihood meth od. This procedure consists of solving centered pseudo-likelihood equa tions, i.e. equations in which the bias of the score function due to t he misspecification is corrected by introducing terms involving its em pirical mean. We show that these estimators may be considered as covar iance estimators, i.e. estimators defined by means of some zero correl ation constraints. These estimators are studied, especially their asym ptotic properties and also their links with moment estimators. (C) 199 8 Elsevier Science S.A. All rights reserved.