Home  >>  Archives  >>  Volume 16 Number 1  >>  st0431

The Stata Journal
Volume 16 Number 1: pp. 197-228

Subscribe to the Stata Journal

Implementing factor models for unobserved heterogeneity in Stata

Miguel Sarzosa
Purdue University
West Lafayette, IN
[email protected]
Sergio Urzúa
University of Maryland
College Park, MD
and National Bureau of Economic Research
Cambridge, MA
[email protected]
Abstract.  We introduce a new command, heterofactor, for the maximum likelihood estimation of models with unobserved heterogeneity, including a Roy model. heterofactor fits models with up to four latent factors and allows the unobserved heterogeneity to follow general distributions. Our command differs from Stata's sem command in that it does not rely on the linearity of the structural equations and distributional assumptions for identification of the unobserved heterogeneity. It uses the estimated distributions to numerically integrate over the unobserved factors in the outcome equations by using a mixture of normals in a Gauss–Hermite quadrature. heterofactor delivers consistent estimates, including the unobserved factor loadings, in a variety of model structures.
Terms of use     View this article (PDF)

View all articles by these authors: Miguel Sarzosa, Sergio Urzúa

View all articles with these keywords: heterofactor, unobserved heterogeneity, factor models, Roy model, maximum likelihood, numerical integration

Download citation: BibTeX  RIS

Download citation and abstract: BibTeX  RIS