Maximum likelihood estimation in graphical models with missing values

Abstract

In this paper we discuss maximum likelihood estimation when some observations are missing in mixed graphical interaction models assuming a conditional Gaussian distribution as introduced by Lauritzen & Wermuth (1989). The approach via the EM algorithm of Little & Schluchter (1985) for the saturated case is expanded to cover the special restrictions in graphical models. A more efficient way to compute the E-step is indicated. The main purpose of the paper is to show that for certain missing patterns the computational effort can be considerably reduced.