Normalize in the Oaxaca Decomposition

[Frederike Freund]

Dear Statalist,
I currently do a Oaxaca Decomposition on mean logarithm wages between women and men.
I used the command "normalize" to solve the Problem of the omitted group choice for the dummy variables.
But I don't know how to interpret the results now. Can anyone explain to me what the command normalize does with the results?
I Have estimates for all the categoryies, including the reference group.
Best regards,
Frederike Freund

[FernandoRios]

Dear Frederike,
I think you should consult the paper that is cited within the oaxaca command. The author does a very detailed explanation oof most of the capabilities and functions in the Oaxaca command.
In any case, the way that helps me to think about the normalization is that the results are being presented as deviations from the grant mean.
Hope this helps
Fernando

[Fabiola]

Dear @FernandoRios,

I’m using the oaxaca command to make a twofold decomposition in Stata 17. I would appreciate it if you could give me some advice about the code.

Since I have categorical independent variables (all of them are binary) I'm using the normalize option to avoid the omitted category bias, but I found that the aggregate results for each independent variable using the normalized effects are the same as the results without it. I also changed the reference category in the model without "normalize", but got the same results.

I would like to know if it is correct and in the case of a dichotomous variable there is no need to use normalize or my code is wrong.

Here is the code I used to get the “normalized” effects

oaxaca sb_auto idade_18 (fem: normalize(fem_d?)) (renda_qui_oaxaca:normalize(renda_qui_oaxaca_d?)) (abvd:normalize(abvd_d?)) (con_dente2:normalize(con_dente2_d?)) (dif_comer2:normalize(dif_comer2_d?)) (prot:normalize(prot_d?)) ndentes, by(escol2_oaxaca) logit weight(0) svy noisily, if subpop_sbauto_oaxaca==1 & ndentes>0

Here is the code without the normalize option (reference category is 0)

oaxaca sb_auto idade_18 fem_d2 renda_qui_oaxaca_d2 abvd_d2 con_dente2_d2 dif_comer2_d2 prot_d2 ndentes, by(escol2_oaxaca) logit weight(0) svy noisily, if subpop_sbauto_oaxaca==1 & ndentes>0

Any support will be very much appreciated.

Best regards,
Fabíola