GMM estimation

[ancia dettox]

Hi,

I'm new in dynamics panel models and I need your help to organise my knowledge. I have 338 observations (13 years and 26 entities). I would like to build dynamics model but how should I step by step test my variables?
Should be it in this way:
1) I add one lag of my dependent variable
2) I add two or more lags of my dependent variable
3) I add some lags of my independent variables
4) I try to find some instruments?
How should I decide which model is the best?


Thank you very much for your help!

[Sebastian Kripfganz]

You might find my recent London Stata Conference presentation useful, in particular the last section on model selection and the reference therein to a paper by Jan Kiviet:

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

[ancia dettox]

Thanks sebastian but I have some doubts again. I think I don't see responses to my questions in your presentation