Skip to main content

Table 1 Different Stata command packages for decomposition of outcome differences between the two groups

From: A detailed explanation and graphical representation of the Blinder-Oaxaca decomposition method with its application in health inequalities

Command Description (estimation_command)
Oaxaca Linear decomposition; the default (linear), logit decomposition (logit), probit decomposition (probit)
Fairlie Logit model; the default (logit), probit model (probit)
Gdecomp Logit model; the default (logit), probit model (probit), Poisson regression (poisson), negative binomial regression (nbreg)
Mvdcmp Probit model (probit), Poisson regression (poisson), negative binomial regression (nbreg), complementary log–log model (cloglog)
Nldecompose Linear regression (regress), logit model (logit), probit model (probit), Ordinal logit model (ologit), Ordinal probit model (probit), Tobit model (tobit), Interval regression (intreg), Truncated Gaussian regression (truncreg), Poisson regression (poisson), negative binomial regression (nbreg), zero-inflated Poisson (zip), zero inflated negative binomial (zinb), Zero-truncated poisson (ztp), Zero-truncated negative binomial (ztnb)