Decomposition Analysis for a Binary Choice Model

Myeong-Su Yun ()

No 145, IZA Discussion Papers from Institute of Labor Economics (IZA)

Abstract: This paper introduces a new and simple decomposition method for a binary choice model that is equivalent to the Blinder-Oaxaca decomposition analysis for wage differentials. The decomposition method is first developed for a single probit model and later generalized to a simultaneous equations model. Using Taylor expansion, we approximate the differences in the probabilities of choosing option 1 over option 0 between two groups in order to find the effects ofthe differences in "each" individual characteristic and the differences in "each" coefficient. We implement this decomposition analysis studying the racial gap in female labor market participation rates. The racial gap of participation rates among women can be almost exclusively explained by the differences in the coefficients.

Keywords: Decomposition analysis; binary choice; probit; selection bias; maximum likelihood estimation; labor market participation (search for similar items in EconPapers)
JEL-codes: C25 C35 J21 (search for similar items in EconPapers)
Pages: 34 pages
Date: 2000-04
New Economics Papers: this item is included in nep-ecm
References: View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
https://docs.iza.org/dp145.pdf (application/pdf)

Related works:
Working Paper: Decomposition Analysis for a Binary Choice Model (2000)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:iza:izadps:dp145

Ordering information: This working paper can be ordered from
IZA, Margard Ody, P.O. Box 7240, D-53072 Bonn, Germany

Access Statistics for this paper

More papers in IZA Discussion Papers from Institute of Labor Economics (IZA) IZA, P.O. Box 7240, D-53072 Bonn, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Holger Hinte ().