I have unbalanced panel data with T= 17 and N =18. I reached to use robust fixed effect model with very good results. I mostly have endogeneity problem due to reversal causality problem as 2 control variables are affected back by the dependent variable. The empirical relevant research papers use GMM to address this problem. I tried to conduct it, however, most of the variables are insignificant. this problem could be due to the small sample size, moderate multicollinearity I have, or other technical issue I cannot figure out. Also, I tried SEM-ML, however the missing data I have make estimation problematic.
I appreciate any little advice could help me in this regard.
thanks in advance !
- Badges
- Science topic
- Similar topics
- Indexes
More Nariman Sayd's questions See All
Similar questions and discussions