Dear Prof. Joao Santos Silva , Prof. Tom Zylkin and dear Statalisters

The purpose of my work is to capture the impact of globalisation on exports. I have a model with one exporter and 154 importers. My dependent variables is exports with a set of standard independent variables, GDP, exchange rate , Globalisation, transportation cost instead of distance and dummy for RTA, language, contiguity, landlocked nations.

Please help me with a few things :
1. While I try to estimate the importer-time fixed effect, I use the command
egen imp_time = group(importer year)
tabulate imp_time, generate(IMPORTER_TIME_FE)
when I use it in the model STATA reports IMPORTER_TIME_FE as an ambiguous observation. What can be the reason for it? Can I deal with it any other way?

2. Since I have just one exporter, shall importer time fixed effect be same as my paired fixed effect?

3. Is there any test to check endogeneity while using PPML estimations?

4. How else can I address the endogeneity with RTA?

5. Is there any robustness check other than RESET test?

6. While going through the posts on statalist I learnt that Prof. Joao suggested one more way to perform RESET test, other than what is suggested on your page, that is,
predict XB, xb
qui su XB
gen XB2 = (XB-r(mean))^2
quietly ppml...
test XB2=0 . What is the difference between the two?

Suggestions are more than welcomed.