Direct and Indirect Effects in a Logit Model

In this article, I discuss a method by Erikson et al. (2005, Proceedings of the National Academy of Science 102: 9730–9733) for decomposing a total effect in a logit model into direct and indirect effects. Moreover, I extend this method in three ways. First, in the original method the variable through which the indirect effect occurs is assumed to be normally distributed. In this article, the method is generalized by allowing this variable to have any distribution. Second, the original method did not provide standard errors for the estimates. In this article, the bootstrap is proposed as a method of providing those. Third, I show how to include control variables in this decomposition, which was not allowed in the original method. The original method and these extensions are implemented in the ldecomp command.

[1]  Natalie Rogoff Ramsöy.  On Education, opportunity, and social inequality , 1975 .

[2]  T. Bauer,et al.  The Blinder–Oaxaca Decomposition for Nonlinear Regression Models , 2008 .

[3]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[4]  David R. Cox,et al.  On class differentials in educational attainment. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[5]  P. Converse,et al.  The American voter , 1960 .

[6]  J. Goldthorpe,et al.  Primary and Secondary Effects in Class Differentials in Educational Attainment , 2007 .

[7]  N. Stern,et al.  The Suntory and Toyota International Centres for Economics and Related Disciplines The Employment of Married Women in the United Kingdom 1970-83 , 2008 .

[8]  Larry M. Bartels.  Beyond the Running Tally: Partisan Bias in Political Perceptions , 2002 .

[9]  M. Buis.  Stata Tip 48: Discrete Uses for Uniform() , 2007 .

[10]  D. Macpherson,et al.  Plant size and the decline of unionism , 1990 .

[11]  Angus Campbell,et al.  The American voter , 1960 .

[12]  Tamás Bartus.  Estimation of Marginal Effects using Margeff , 2005 .

[13]  Ben Jann.  FAIRLIE: Stata module to generate nonlinear decomposition of binary outcome differentials , 2006 .

[14]  An Extension of the Blinder-Oaxaca Decomposition to a Continuum of Comparison Groups , 2007 .

[15]  R. Fairlie.  An Extension of the Blinder-Oaxaca Decomposition Technique to Logit and Probit Models , 2006, SSRN Electronic Journal.

[16]  Maarten L. Buis.  Predict and Adjust with Logistic Regression , 2007 .

[17]  Myeong-Su Yun.  Decomposing Differences in the First Moment , 2003, SSRN Electronic Journal.

[18]  T. Bauer,et al.  An extension of the Blinder–Oaxaca decomposition to nonlinear models , 2006 .