11-20-2013 10:42 AM
I am new to sas. I used sas to form my own FF portfolios for the Chinese stock markets.
So i am ok with sas when it's about data management but can't do GMM estimation properly and i had a hard time figuring a way.
Basically, I want to estimate an asset pricing model using GMM:
But i don't know how to properly specify the moment conditions using Proc model.
It is about implementing a linear factor asset pricing model.
I have nine Fama-French portfolios and three risk factors.
I need to run a time-series regressions to get the coefficient estimates on three risk factors for each of the nine portfolio.
and the residuals should be orthogonal to the risk factors. This is the first and second moment conditions as in the screenshot of the book.
Then i need to run a cross-section regression. that is to regress coefficient estimates from the above regression (which becomes the right hand variables) on the
average excess return of the portfolios. this is the third moment conditions.
The reason for using GMM is that the covariance matrix is supposed to take care the generated regressor problem and gives me robust inference.
But i really don't know how to do it using Proc model. I did it in all the way imaginable, but the results i get are nonsensical, so they are obviously wrong.
please, see the attached sas codes, they are obviously wrong. But i am able to specify the first nine time series regression and don't know how to proceed further.
I think what i need to do is to saved the estimated coefficients and the VCV of the parameter estimates and somehow tell sas to use that information in
estimating the third moment conditions.
I attaches the the screenshot from cochrane's book where he specifies the moment conditions and what the spreadsheet look like.
Any help and suggestion is greatly appreciated.
Thank you very much.
11-22-2013 05:08 PM
Not sure if this is useful, but you may want to check out: http://home.business.utah.edu/finmll/fin787/programs/gmmassetpricingtests.sas