Adj R squared in Fama-MacBeth Regression

[mexes]

Hi everybody

How can I get the adj R squared within this code when I make a FMB Regression? I tried it with the option ods output FitStatistics = fitstats, but it did not work correctly. Thanks for the help.

ods listing close;

output parameterestimates=pe;

proc reg data=test;

by year;

model y= x; run;

quit;

ods listing;

proc means data=pe mean std t probt;

var estimate; class variable;

run;

proc sort data=pe; by variable; run;

%let lags=3;

ods output parameterestimates=nw;

ods listing close;

proc model data=pe;

by variable;

instruments / intonly;

estimate=a;

fit estimate / gmm kernel=(bart,%eval(&lags+1),0) vardef=n; run;

quit;

ods listing;

[SteveDenham]

I really don't have an answer, but I would bet that someone on the Forecasting and Econometrics forum would be able to help with the PROC MODEL part.  You should consider reposting this in that forum.

Steve Denham

[AncaTilea]

Hi.

if you do a quick google search on your request you will see that there is some sort of code (that looks similar to yours) from Jie Cao:

http://ihome.cuhk.edu.hk/~b121456/tools/FF_reg.txt

Maybe it will help?

Anca

[Reeza · Accepted solution]

Are you looking for the standard adj r from proc reg or proc model (which I know nothing about)? Or another type of calculation?

[HHZ]

*add one option like the following will give you adjusted R-sq in the dataset "adjrsq" together with other default statistics;

*i use it by myself, and it works;

ods listing close;

output parameterestimates=pe  fitstatistics=adjrsq;

proc reg data=test;

by year;

model y= x; run;

quit;

ods listing;