Finite Mixture Models for Linked Survey and Administrative Data: Estimation and Post-Estimation

38 Pages Posted: 29 May 2021

See all articles by Stephen P. Jenkins

Stephen P. Jenkins

London School of Economics & Political Science (LSE) - Department of Social Policy and Administration; Institute for the Study of Labor (IZA); University of Essex - Institute for Social and Economic Research (ISER)

Fernando Rios Avila

Bard College - The Levy Economics Institute

Abstract

Researchers use finite mixture models to analyze linked survey and administrative data on labour earnings (or similar variables), taking account of various types of measurement error in each data source. Different combinations of error-ridden and/or error-free observations characterize latent classes. Latent class probabilities depend on the probabilities of the different types of error. We introduce a set of Stata commands to fit a general class of finite mixture models to fit to linked survey-administrative data We also provide post-estimation commands for assessment of reliability, marginal effects, data simulation, and prediction of hybrid earnings variables that combine information from both data sources.

JEL Classification: C81, C83, D31

Suggested Citation

Jenkins, Stephen P. and Rios Avila, Fernando, Finite Mixture Models for Linked Survey and Administrative Data: Estimation and Post-Estimation. IZA Discussion Paper No. 14404, Available at SSRN: https://ssrn.com/abstract=3855968 or http://dx.doi.org/10.2139/ssrn.3855968

Stephen P. Jenkins (Contact Author)

London School of Economics & Political Science (LSE) - Department of Social Policy and Administration ( email )

Houghton Street
London, England WC2A 2AE
United Kingdom

Institute for the Study of Labor (IZA)

P.O. Box 7240
Bonn, D-53072
Germany

University of Essex - Institute for Social and Economic Research (ISER) ( email )

Wivenhoe Park
Colchester CO4 3SQ
United Kingdom
+44 120 687 3374 (Phone)
+44 120 687 3151 (Fax)

Fernando Rios Avila

Bard College - The Levy Economics Institute ( email )

Blithewood, Bard College
Annandale, NY 12504-5000
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
20
Abstract Views
196
PlumX Metrics