Testing the Equality of the Regression Coefficients After PPMLHDFE

[Yang Jianbing Wang]

I tried to estimate a PPML gravity model of bilateral trade with country-time fixed effects by -ppmlhdfe-, and ran the same model for two subsamples.

My codes look like this:

ppmlhdfe tradevalueus x controls if D==1, a(i.year#i.iso3num_o i.year#i.iso3num_d)
ppmlhdfe tradevalueus x controls if D==0, a(i.year#i.iso3num_o i.year#i.iso3num_d)

Now, I want to test whether the coefficients of x from the two above regressions are equal, but it seems that -suest- can not be used under this situation. (I tried, but STATA reported error.)

Could anyone please give me some advice about how to conduct this test? Thanks in advance.

[Andrew Musau]

ppmlhdfe is from SSC (FAQ Advice #12). You can probably adopt the same approach as reghdfe (SSC) illustrated in https://www.statalist.org/forums/for...erent-outcomes. No data example, you will increase your chances of getting helpful replies by providing one (see the referenced FAQ Advice for details).

[Yang Jianbing Wang]

ppmlhdfe is from SSC (FAQ Advice #12). You can probably adopt the same approach as reghdfe (SSC) illustrated in https://www.statalist.org/forums/for...erent-outcomes. No data example, you will increase your chances of getting helpful replies by providing one (see the referenced FAQ Advice for details).

Thank you very much! I'll try this. Have a good weekend!

[Andrew Musau]

Also see https://www.statalist.org/forums/for...h-fixed-effect