Estimating Ordered Categorical Variables Using Panel Data: A Generalized Ordered Probit Model with an Autofit Procedure

14 Pages Posted: 15 Jun 2010 Last revised: 1 Apr 2011

See all articles by Christian Pfarr

Christian Pfarr

University of Bayreuth

Andreas Schmid

University of Bayreuth

Udo Schneider

Techniker Krankenkasse

Date Written: June 14, 2010

Abstract

Estimation procedures for ordered categories usually assume that the estimated coefficients of independent variables do not vary between the categories (parallel-lines assumption). This view neglects possible heterogeneous effects of some explaining factors. This paper describes the use of an autofit option for identifying variables that meet the parallel-lines assumption when estimating a random effects generalized ordered probit model. We combine the test procedure developed by Richard Williams (gologit2) with the random effects estimation command regoprob by Stefan Boes.

Keywords: generalized ordered probit, panel data, autofit, self-assessed health

JEL Classification: C23, C25, C87, I10

Suggested Citation

Pfarr, Christian and Schmid, Andreas and Schneider, Udo, Estimating Ordered Categorical Variables Using Panel Data: A Generalized Ordered Probit Model with an Autofit Procedure (June 14, 2010). Available at SSRN: https://ssrn.com/abstract=1624954 or http://dx.doi.org/10.2139/ssrn.1624954

Christian Pfarr (Contact Author)

University of Bayreuth ( email )

Universitatsstr 30
Bayreuth, D-95447
Germany

HOME PAGE: http://www.fiwi.uni-bayreuth.de

Andreas Schmid

University of Bayreuth ( email )

Universit├Ątsstra├če 30
Bayreuth, 95447
Germany

Udo Schneider

Techniker Krankenkasse ( email )

Bramfelder Str. 140
D-22305 Hamburg
Germany

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
398
Abstract Views
1,670
rank
80,539
PlumX Metrics