Hello,   I'm running the following regression (a Fama MecBeth regression):   proc sort data=WORK.QUERY out=FM_quadric_reg1;  by gvkey; run;   PROC REG DATA=FM_quadric_reg1   outest=FM_quadric_reg011 noprint outseb; MODEL y= x1 x2;    by gvkey ;   RUN; QUIT; proc means data=FM_quadric_reg011 n mean t probt;  where _TYPE_ = 'PARMS'; run;   Now I want to winsore the outliers: for both beta 1 , beta 2, and the intercept, I want to turn values of that exceed mean  plus 3 std dev to the value of mean plus 3 std dev and to turn the values that below mean minus 3 std dev to the value of mean minus 3 std dev. I want to do it for both beta 1 (the coefficient of x1) , beta 2 (the coefficient of x2) and the intercept. could you please assist in writing the code for that?   Thank you, Lior   ... View more

   Hello,  ֲ I wrote the following regression code:   proc glm data= reg_roa ; absorb gvkey01 ;class year;   model ROA= T DM DM_X /noint solution; run; quit;/* I would like to receive the covariance of ֲ the coefficients ֲ of T and DM_X (this covariance will be used in order to test if the sum of coefficients of T and DM_X equal to zero).   Do you know what I have to add to my code in order to receive the covariance?   Thanks, Lior ... View more

Hello, ֲ I run the regression: Y = α + β1 X + β2 Dummy variable*X + β3 Dummy variable + ε β1 is negative and β2 is positive. I want to verify that the sum : β1+β2 is positive and significant, or ֲ in other words, ֲ  that β2>β1 and that the difference is significant.   According to the ֲ values the coefficients , ֲ indeed ֲ β2>β1 but I'm ֲ looking ֲ for statistical test that verify that the difference is significant.   Does  SAS perform this kind of test?   Thank You, Lior ... View more

Hallow, I run a quadric regression: Y = β1 X + β2〖〖X 〗^2 + ε The Extremum of Parabola is  (–β1 )/2β2   Both   β1 and β2 are significance, but as I understood it's not enough to determined that the Extremum of Parabolaֲ  which equal toֲ   β1 and β2 is significant. Is there aֲ  SAS procedure that execute t test for Extremum of Parabolaֲ  ?   Thank you, Lior   ... View more