Hello everyone.
I've panel data including 10 years and 74 units. I'm trying difference GMM but there is a problem. When I run primitive command, both ar(1) and ar(2) is statistically significant. So, I'm adding second lagged of dependant variable in regresson. Then ar(2) is becoming insignificant (as it should be). But, and now second lagged variable's estatimated coefficient is statistically insignificant (first lagged is significant). is it a problem? if it is, what should I do? Can I calculate long-run coefficients with insignificant second lagged of dependant variable? Thanks in advance.
I've panel data including 10 years and 74 units. I'm trying difference GMM but there is a problem. When I run primitive command, both ar(1) and ar(2) is statistically significant. So, I'm adding second lagged of dependant variable in regresson. Then ar(2) is becoming insignificant (as it should be). But, and now second lagged variable's estatimated coefficient is statistically insignificant (first lagged is significant). is it a problem? if it is, what should I do? Can I calculate long-run coefficients with insignificant second lagged of dependant variable? Thanks in advance.
