BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
lior
Calcite | Level 5

Hello,

I run proc panel procedure (I have panel data and I want to consider fixed effects). and its work fine.

but I don't know how to enter white's (1980) correction to this procedure.

(all the examples to white's correction are in proc model procedure).

anyone happens to know how to do this?

Thanks,

Lior

1 ACCEPTED SOLUTION

Accepted Solutions
SteveDenham
Jade | Level 19

Why not:

proc panel data=invest.table_regressionfinal ;

id GVKEY DATADATE;

   model shareprice_ending_of_tm_f_qtr= bv EPSPXQ/fixone hccme=4;

    run;

This should work (at least based on the documentation).

Steve Denham


View solution in original post

5 REPLIES 5
SteveDenham
Jade | Level 19

Look up the HCCME= option for the MODEL statement in PROC PANEL.  HCCME=4 uses the Arellano version of the White correction.

Steve Denham

lior
Calcite | Level 5

Hi,

Thanks,  I found this statement in the web but  I havn't found statement that combined both fixed Effect and White's correction.

The statement with fixed effect is:

proc panel data=invest.table_regressionfinal ;

id GVKEY DATADATE;

   model shareprice_ending_of_tm_f_qtr= bv EPSPXQ/fixone ;

      run;

And the statement with HCCME is:

proc panel data=invest.table_regressionfinal ;

id GVKEY DATADATE;

   model shareprice_ending_of_tm_f_qtr= bv EPSPXQ/pooled hccme=4;

    run;

Do you happen to know how to combine those two in a way it will make sense ?

Thanks,

Lior

SteveDenham
Jade | Level 19

Why not:

proc panel data=invest.table_regressionfinal ;

id GVKEY DATADATE;

   model shareprice_ending_of_tm_f_qtr= bv EPSPXQ/fixone hccme=4;

    run;

This should work (at least based on the documentation).

Steve Denham


lior
Calcite | Level 5

Yes, its working.

Thank you very much,

Lior

ets_kps
SAS Employee

Steve thanks for the answer here.  One additional piece of information might be useful for you loir.

Within the PANEL procedure, a new feature implements a more general form of the sandwich estimator for consistent SE's. 

These options are under the HAC= option (Hetero and Autocorrelated SE's).  For a super quick and dirty robust SE, add HAC=neweywest  to the model statement. 

SAS/ETS(R) 13.2 User's Guide

SAS Innovate 2025: Call for Content

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!

Submit your idea!

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.

Discussion stats
  • 5 replies
  • 2220 views
  • 4 likes
  • 3 in conversation