An extension of the Blinder-Oaxaca decomposition technique to logit and probit models

By R. Fairlie. Social Science Research Network, 2005

1,258 citations recorded by the source corpus.

The Blinder-Oaxaca decomposition technique is widely used to identify and quantify the separate contributions of group differences in measurable characteristics, such as education, experience, marital status, and geographical differences to racial and gender gaps in outcomes. The technique cannot be used directly, however, if the outcome is binary and the coefficients are from a logit or probit model. I describe a relatively simple method of performing a decomposition that uses estimates from a logit or probit model. Expanding on the original application of the technique in Fairlie [3], I provide a more thorough discussion of how to apply the technique, an analysis of the sensitivity of the decomposition estimates to different parameters, and the calculation of standard errors. I also compare the estimates to Blinder-Oaxaca decomposition estimates and discuss an example of when the Blinder-Oaxaca technique may be problematic.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/239f304d36838049b3c8614f98cd1152b7fd7812

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Decomposing the Ins and Outs of Cyclical Unemployment (2012, neutral): “(4)Approximate decomposition results for Logit and Probit models can be derived by employing the decomposition method proposed by Fairlie (2003). These results do not differ qualitatively from the results presented in our paper.”
Gender, Risk, and Venture Creation Intentions (2015, methodology): “For this purpose an alternative is proposed (Fairlie, 2005): (2) with j N being the sample size for gender j.”
Disability and the Rural Labor Market in India: Evidence for Males in Tamil Nadu (2008, methodology): “Because the dependent variable (employment) is binary, we use non-linear decomposition techniques proposed by Fairlie (1999, 2003) rather than the traditional Oaxaca-Blinder decomposition approach (Oaxaca, 1973).”
The erosion of union membership in Germany: determinants, densities, decompositions (2006, methodology): “We investigate (1) the changes of NUD over time and (2) the differences in NUD between East and West Germany by means of the Blinder–Oaxaca decomposition technique (Blinder 1973; Oaxaca 1973), which we adapt to the nonlinear probit estimator similar to Fairlie (2005). In order to decompose”
Infrastructure and the Rural—urban Divide in High-speed Residential Internet Access (2007, background): “As Fairlie (2003) notes, the sensitivity of the order in which the variables are introduced is dependent on the initial location of the estimate on the logistic distribution and the movement of the estimate along the distribution by switching characteristics of rural and urban households.”
The Blinder–Oaxaca Decomposition for Nonlinear Regression Models (2008, methodology): “Several studies have developed and applied Blinder–Oaxaca decompositions for models with binary dependent variables (Gomulka and Stern 1990; Even and Macpherson 1990; Yun 2004; Fairlie 1999, 2005).”
7. Multivariate Decomposition for Hazard Rate Models (2009, methodology): “Various methods have been proposed to overcome this dependency, including averaging over all possible orders of covariate replacement (Fairlie 2005) and by determining the relative contribution of each variable to each component using a set of appropriately constructed weights (Even and Macpherson…”
Measuring Racial/Ethnic Disparities in Health Care: Methods and Practical Issues (2012, positive): “These methods have been widely used in linear regression models (Blinder 1973; Oaxaca 1973), and numerous applications have grappled with the difficulties inherent in applying decomposition methods in nonlinear models (Yun 2004; Fournier 2005; Fairlie 2005).”
Hypothesis tests when decomposing differences in the first moment (2005, neutral): “…free from path dependency, unlike a sequential replacement approach that computes the contribution of an individual variable or its coefﬁcient to the differences in the ﬁrst moments by switching values of one group with those of a comparison group, such as in the method proposed by Fairlie [4].”
What Explains the Stagnation of Female Labor Force Participation in Urban India? (2015, methodology): “…International M onetary Fund on Septem ber 29, 2015 http://w ber.oxfordjournals.org/ D ow nloaded from The estimates are further used to decompose the stagnation of FLFP between 1987 and 2011 into contributions by different covariates and changes in behavior and unobservables (Fairlie 2006).”
Is There a Disability Gap in Employment Rates in Developing Countries (2012, methodology): “Since a logit model will be used in the analysis, the non-linear decomposition technique proposed by Fairlie (1999; 2003) will be used11.”
Immigration and Entrepreneurship (2015, methodology): “…such as business ownership rates, an alternative non-linear decomposition technique originally developed in Fairlie (1999) and further discussed in Fairlie (2005) is used.13 The technique is used when logit or probit regressions are estimated to identify the determinants of business ownership or…”