GMM related problem

[Prakashani Singh]

When I am running my baseline regression with FGLS I am getting significant results but when I am doing the same thing with two-step system GMM then the results are insignificant. Also, I have problems understanding how to use instrumental variables. Please help me with appropriate commands.

[Sebastian Kripfganz]

FGLS and system GMM are different estimation methods. They are usually not easily interchangeable due to different underlying assumptions. In any case, GMM estimators often have larger variances, which might contribute to the observation that your results are no longer statistically significant.

Assuming that you have panel data, the following presentation might be insightful regarding GMM estimation:

• Kripfganz, S. (2019). Generalized method of moments estimation of linear dynamic panel data models. Proceedings of the 2019 London Stata Conference.

[Prakashani Singh]

Thank you. I want to know which command of gmm I should use if N=68 and T=48 in my panel dataset.