A Logit Model with Missing Information Illustrated by Testing for Hidden Unemployment in Transition Economies

In an important paper, <link rid="b4">Dempster, Laird and Rubin (1977)</link> showed how the expectation maximization (EM) algorithm could be used to obtain maximum likelihood estimates of parameters in a multinomial probability model with missing information. This article extends Dempster, Laird and Rubin's work on the EM algorithm to the estimation of a multinomial logit model with missing information on category membership. We call this new model the latent multinomial logit (LMNL) model. A constrained version of the LMNL model is used to examine the issue of hidden unemployment in transition economies following the approach of <link rid="b6">Earle and Sakova (2000)</link>. We found an additional 0.5% hidden unemployment among workers describing themselves as self-employed in the transition economies of Central and Eastern Europe. Copyright 2006 Blackwell Publishing Ltd.