Finite mixture distributions, sequential likelihood and the EM algorithm
Repository Usage Stats
A popular way to account for unobserved heterogeneity is to assume that the data are drawn from a finite mixture distribution. A barrier to using finite mixture models is that parameters that could previously be estimated in stages must now be estimated jointly: using mixture distributions destroys any additive separability of the log-likelihood function. We show, however, that an extension of the EM algorithm reintroduces additive separability, thus allowing one to estimate parameters sequentially during each maximization step. In establishing this result, we develop a broad class of estimators for mixture models. Returning to the likelihood problem, we show that, relative to full information maximum likelihood, our sequential estimator can generate large computational savings with little loss of efficiency.
More InfoShow full item record
Professor of Economics
Professor Arcidiacono specializes in research involving applied microeconomics, applied economics, and labor economics. His research primarily focuses on education and discrimination. His work focuses specifically on the exploration of a variety of subjects, such as structural estimation, affirmative action, minimum wages, teen sex, discrimination, higher education, and dynamic discrete choice models, among others. He recently received funding from a National Science Foundation Grant for his pro