Turn on suggestions

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

Showing results for

- Home
- /
- Analytics
- /
- Forecasting
- /
- Fama Macbeth regression using data where few independent variables are...

Options

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

- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content

Posted 10-11-2017 03:21 AM
(2735 views)

Hi everyoneI

am trying to run Fama Macbeth regression using data where few independent variables (risk factors) are shared across stocks each month, and others are not (Price, Size, Skenwss, Idiosyncratic Volatility).

I guess it happens because the factor must vary across cross-sectional units, i.e., across stocks in a month.

Ri,t=Bi,t(RMRF)+Bi,t(SMB)+Bi,t(HML)+logPRICEt-1+logBTMt-1+IVt-1

In this regression RMRF, SMB and HML are same for each stock in a month but logPRICE, logBTM and IV are different.

Thanks for your help.

Best Regards,

Cheema

4 REPLIES 4

- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content

I am trying to run Fama Macbeth regression using data where few independent variables (risk factors) are shared across stocks each month, and others are not (Price, Size, Skenwss, Idiosyncratic Volatility).

I guess it happens because the factor must vary across cross-sectional units, i.e., across stocks in a month.

Ri,t=Bi,t(RMRF)+Bi,t(SMB)+Bi,t(HML)+logPRICEt-1+logBTMt-1+IVt-1

In this regression RMRF, SMB and HML are same for each stock in a month but logPRICE, logBTM and IV are different.

Thanks for your help.

Kind Regards,

Cheema

- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content

You can add "month" as a class variable, and add interaction between (Price, Size, Skenwss, Idiosyncratic Volatility) and month. To add an interaction effect, you just do price*month. So in your example, the regression function will be:

Ri,t=Bi,t(RMRF)+Bi,t(SMB)+Bi,t(HML)+ (logPRICEt-1)*month +(logBTMt-1)*month + (IVt-1)*month

In this way, it will estimate different parameters for PRICE, BTM and IV each month. Don't forget to claim month as a class variable in your model.

Check out the time series and forecasting tasks in SAS Studio! They provide an easy point-and-click interface for Time Series Data Preparation, Time Series Exploration, and Time Series Modeling and Forecasting.

- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content

Hi Puwang,

Sorry, my question might be bit unclear. In Fama Macbeth regression, the independent variable need to vary across stocks in each time period. However, in my case, the dependent variables like SMB, HML and RMRF are same for all the stocks in a given time periods. Therefore, I am wondering how to use Fama Macbeth regression in this situation. I estimate beta for each stocks first and then run the Fama Macbeth regression. By estimating beta for each stock will make the independent variable vary across stocks in each time period; therefore might be possible to use Fama Macbeth regression. Can you please advise me if this process sounds fine?

Thanks for your help.

Best,

Cheema

- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content

Hi Cheema,

I am facing the same problem now. So, I am wondering if you were able to solve yours.

I am trying to run a regression using Fama-French Factors and I have coefficients that are zero because SAS is unable to compute correlation statistics for variable Residual.

can you please share your solution if you already found one?

Are you ready for the spotlight? We're accepting content ideas for **SAS Innovate 2025** to be held May 6-9 in Orlando, FL. The call is **open **until September 25. Read more here about **why** you should contribute and **what is in it** for you!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.