EViews.com

I am referring to the the Blundell Bond System GMM estimator for dynamic panel data. How may I use it in EViews?

Thanks.

GMM refers to generalized method of moments. I would like to know whether the default GMM is actually called the system GMM.

And let me know any textbook or reference that would provide the GMM, especially the overidentification tests (Sargan and Hansen tests). Thanks.

Dave

I would like to know if there is any difference between system GMM and difference GMM. I realise that we can choose to difference option to control for fixed effects. Secondly, I wonder if anyone can suggest textbooks or references where I can find the Sargen and Hansen tests for overidentification ...

When someone mentions system GMM and difference GMM, are they the same? If not, please let me know how to run system GMM using EViews?! What options to choose in the GMM procedure.

Thanks.

Dave

I realise that the EViews manual (Guide 2) has a single paragraph describing the J-statistics/Sargan statistics from GMM estimation. As I need to conduct the Sargan test for over-identification problem, I hope to get the whole procedure. Is there any other manuals that describe the Sargan test in mo...

I am using the Generalized Method of Moment estimation. I notice that there are 2 ways to conduct the analysis: (1) enter the explanatory variables and instrumental variables in different columns, and choose the relevant features (cross-section, time, GMM weight, coefficient covariance method, etc.)...

After I perform the IV estimation, the manual indicates that I can conduct the IV diagnostics and tests by clicking View/IV disagnostics/......
But I can't find this option in my EViews version 8. Does anyone know why? I have a panel dataset for IV estimations.

Are there any details about choosing the weighting matrix in GMM? I could not find any in Illustrated EViews Manual!

Thanks

I chose 2SLS as weighting matrix. Is it the reason why I got the same results??

EV

I am using the 2-stage least squares method to control for endogeneity problem. Because GMM can also resolve this problem and control for heteroskedasticity and serial correlation, I re-run the data using GMM. But it turns out the 2SLS and GMM results are exactly the same. Am I setting certain GMM f...