turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Stat Procs
- /
- many mistakes in my F-test part. help me please. t...

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

04-24-2013 12:07 PM

here is some explain about my question. I need some help. I am kind of following Fama French (1993). I have 50 portfolios. I have to run a time series regression of return of each portfolio on Rm-Rf, SMB, HML. To test 3 factor model of FF, I have to test whether the intercepts in each regression above are jointly significantly different from 0. To do that, the best way is to use Gibbons, Ross, Shanken (1989) test. First I calculate the covariance matrix of the 4 risk factors using proc corr and output the matrix using ods function. Then I calculate the covariance matrix of error terms using proc syslin - SUR. (I am not sure how big a system can proc syslin support) Finally, I use proc iml to calculate the GRS F-Stat. Thank you very much. Regards, Duong *