Help with interpretation of gravity equation using palm

[Julia Veje]

Hello,

I was wondering if anybody could help me how to interpret the coefficients of my gravity equation. I have used the ppml for estimation with time and country fixed effects and specifically i am trying to estimate the effect of the single market. MY model:
ppml rtrade log_distance loggdp_imp loggdp_eks colony comlang_off contig EEA aar_* ex_dum_* , cluster(dist)

aar_* is time fixed effects ex_dum_* is country fixed effects.
rtrade is the trade volume in mio. US$ in levels!
log_distance, loggdp_eks loggdp_imp are distance, GDP for exporter and GDP for importer country, all three are ing log.
EEA is my FTA dummy, with the value 1 if both countries are a member for the single market.
colony, comlang_off and contig are dummies (former colony, common official language and common border)

result after running my model:

rtrade = -0,38*log_distance + 0,85*loggdp_imp + 0,38*loggdp_eks +1,14*colony - 0,40*comlang_off - 0,5*contig + 0,6*EEA

Especially how to interpret EEA and distance and gdp variables (as they are in logs)

I have read in baier and bergstrand (2007) the EEA variable should be interpret as: (e^0,6-1)*100 = 82 % higher trade volume due to the single market - is this correct?
as my model is linear log i would think the interpretation for log distance is: -0,38/100 = -0,0038 mio. US$ lower trade due to 1 % larger distance?

Hope you understand my question and someone can help (my thesis supervisor is not much help)

Best regards Julia

[Joao Santos Silva]

Julia,

The interpretation of EEA is correct, but the interpretation of the log distance is wrong: this coefficient is just an elasticity so it gives you the percent change in trade associated a 1% increase in distance.

Best wishes,

Joao

[Julia Veje]

Joao - thank you for replying! This was very useful! Is this also the case when the model is level - log? This is just what i have been told, but did wonder a bit.. Does it have anything to do with the estimation technique i am using?

[Julia Veje]

Moreover, i was wondering - as i have a panel data, would you say that it is the yearly change in trade? or the average yearly change in trade? Fx. with the EEA variable: so being in the EEA trade increases by 82 % on average or?

Thanks!

Best regards Julia

[Joao Santos Silva]

Dear Julia,

The interpretation of the parameters estimated by PPML is as in a log-log model estimated by OLS. Parameters in a level-log model estimated by OLS would have a very different interpretation.

Best wishes,

Joao

[Julia Veje]

Oh thank you! That makes sense

Best regards Julia