Blinder-Oaxaca Decomposition for Tobit Models

Working Paper: CEPR ID: DP5309

Authors: Thomas Bauer; Mathias Sinning

Abstract: In this paper, a decomposition method for Tobit-models is derived, which allows the differences in a censored outcome variable between two groups to be decomposed into a part that is explained by differences in observed characteristics and a part attributable to differences in the estimated coefficients. The method is applied to a decomposition of the gender wage gap using German data

Keywords: Blinder-Oaxaca decomposition; Tobit model; wage gap

JEL Codes: C24; J31


Causal Claims Network Graph

Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.


Causal Claims

CauseEffect
observable characteristics (C90)wage outcomes (J31)
differences in estimated coefficients (C51)wage outcomes (J31)
Tobit decomposition method (C69)results (Y10)
Blinder-Oaxaca decomposition (J79)results (Y10)

Back to index