0
$\begingroup$

I am examining one country over a period of 10 years. I am interested to see whether GDP_growth had a heterogeneous effect on wages across people with different educational background. The code below show my model. My question is whether it is plausible to use the gdp_growth in this design? If not, is there any alternative?

In Stata:

xtset id year, yearly
xtreg wage age sex i.educ##c.gdp_growth, fe

In R

 plm(wage ~ age + sex + educ + educ*gdp_growth, data=df, 
 index=c("id", "year"), model="within")
Improve this question
$\endgroup$
3
  • $\begingroup$ Hi jad, can you please tag this question with the software you are using? $\endgroup$
    – Fato39
    Commented Dec 18, 2020 at 20:30
  • $\begingroup$ Does education change for a person over time? If it does not, the direct effect is not separately identified (it gets removed by the demeaning). The interaction coefficient may still be estimable, but it's not clear what plausible means here. Do you mean plausibly causal given what else in the model and some assumptions about how people choose their schooling? $\endgroup$
    – dimitriy
    Commented Dec 19, 2020 at 1:26
  • $\begingroup$ Education does change in the model. If someone gets a university degree, hence an increase in their salaries later on, the model can catch it. So if i understood you right, it is plausible to put the macro indicator in the model? What i mean is, whether an economic expansion/contraction gives more benefit to one educational group over the other $\endgroup$
    – Jack
    Commented Dec 19, 2020 at 8:29

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.