Identification and Decompositions in Probit and Logit Models

13 Pages Posted: 5 Feb 2017

See all articles by Chung Choe

Chung Choe

Hanyang University

SeEun Jung

Inha University - Department of Economics

Ronald L. Oaxaca

University of Arizona - Department of Economics; IZA Institute of Labor Economics

Abstract

Probit and logit models typically require a normalization on the error variance for model identification. This paper shows that in the context of sample mean probability decompositions, error variance normalizations preclude estimation of the effects of group differences in the latent variable model parameters. An empirical example is provided for a model in which the error variances are identified. This identification allows the effects of group differences in the latent variable model parameters to be estimated.

Keywords: decompositions, probit, logit, identification

JEL Classification: C35, J16, D81, J71

Suggested Citation

Choe, Chung and Jung, SeEun and Oaxaca, Ronald L., Identification and Decompositions in Probit and Logit Models. IZA Discussion Paper No. 10530. Available at SSRN: https://ssrn.com/abstract=2911468

Chung Choe (Contact Author)

Hanyang University ( email )

Ansan
Korea, Republic of (South Korea)

HOME PAGE: http://https://sites.google.com/site/choechung/home

SeEun Jung

Inha University - Department of Economics ( email )

253 Yonghyun-dong
Nam-gu Incheon 402-751
Korea

Ronald L. Oaxaca

University of Arizona - Department of Economics ( email )

McClelland Hall
Tucson, AZ 85721-0108
United States
520-621-4135 (Phone)
520-621-8450 (Fax)

IZA Institute of Labor Economics

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

Register to save articles to
your library

Register

Paper statistics

Downloads
54
Abstract Views
226
rank
373,087
PlumX Metrics