Heckman Procedure for Gender Wage Gap (Oaxaca Decomposition)

[Manisha Kapoor]

I am trying to decompose the gender wage gap into explained and unexplained factors using the Blinder Oaxaca decomposition technique using labour survey data. For the same, I ran the following command:
oaxaca log_monthlywages_salary_casual num_frml_edu tech_deg exp_n expsq_n mar_18 ss, by(gender) svy pooled
For this I had restricted my sample to wage earners.
After reading more literature I realised the selectivity bias and want to correct using the heckman two step procedure. Since my sample is restricted to wage earners and I had dropped all other categories such as unemployed, not willing to work, self-employed etc my lfpr (dependent variable) for the probit regression for heckman will always be 1. Should I expand the sample for this and then restrict it back for the Oaxaca eqn?

[Manisha Kapoor]

Can someone also explain the treatment of self employed in the heckman equation?

[Sinem Sefil]

I am trying to decompose the gender wage gap into explained and unexplained factors using the Blinder Oaxaca decomposition technique using labour survey data. For the same, I ran the following command:
oaxaca log_monthlywages_salary_casual num_frml_edu tech_deg exp_n expsq_n mar_18 ss, by(gender) svy pooled
For this I had restricted my sample to wage earners.
After reading more literature I realised the selectivity bias and want to correct using the heckman two step procedure. Since my sample is restricted to wage earners and I had dropped all other categories such as unemployed, not willing to work, self-employed etc my lfpr (dependent variable) for the probit regression for heckman will always be 1. Should I expand the sample for this and then restrict it back for the Oaxaca eqn?

Could you find an answer to this question?

[Rich Goldstein]

there are at least 3 user-written commands that are relevant here: oaxaca, nldecompose and oaxaca_rif; use -search- or -findit- to locate and download

[Rattiya Lippe]

I am trying to decompose the gender wage gap into explained and unexplained factors using the Blinder Oaxaca decomposition technique using labour survey data. For the same, I ran the following command:
oaxaca log_monthlywages_salary_casual num_frml_edu tech_deg exp_n expsq_n mar_18 ss, by(gender) svy pooled
For this I had restricted my sample to wage earners.
After reading more literature I realised the selectivity bias and want to correct using the heckman two step procedure. Since my sample is restricted to wage earners and I had dropped all other categories such as unemployed, not willing to work, self-employed etc my lfpr (dependent variable) for the probit regression for heckman will always be 1. Should I expand the sample for this and then restrict it back for the Oaxaca eqn?

Could you find a solution on this case? I am encountering the similar case. Thank you

[Maxence Morlet]

Waiting for someone to answer this question in a better manner, perhaps perform a Heckman estimator and then do the decomposition manually.

The Blinder-Oaxaca decomposition as it is carried out currently has come under heavy fire however, see this article: https://www.nber.org/system/files/wo...8466/w8466.pdf

Also note that another community contributed command exists for panel data:

xtoaxaca

.