Dear all,

I am dealing with following fixed effect regression:

Gini Index = B0 + B1(Tradeshare) + B2(Rule of Law Index) + B3(Tradeshare * Rule of Law Index) + (control variables) + i.year

Info:
- All variables are continuous
- The Y variabel (Gini Index) is level (i.e. not logged)

As the Tradeshare has a very skew distribution I would like to log the variable to make it more normal distibuted. However, I am not sure whether it is possible to make an interaction term between Tradeshare and Rule of Law if Tradeshare is logged while Rule og Law is not? And how should I then interpret the interaction term?



Thanks in advance

Best from
Trine