How can I get an output from PROC GLM to be like below:
VarName RSQUARE height_MEAN Coeff Var
weight xx xxx ww
sex yy yyy www
It is easy in proc reg but I don't know how to do it in proc glm.
Thank you for your response.
/* 1. transpose from wide (Y, X1 ,...,X100) to long (varNum VarName Y Value) */
data Long;
set Wide; /* <== specify data set name HERE */
array x [*] x1-x&nCont; /* <== specify explanatory variables HERE */
do varNum = 1 to dim(x);
VarName = vname(x[varNum]); /* variable name in char var */
Value = x[varNum]; /* value for each variable for each obs */
output;
end;
drop x:;
run;
/* 2. Sort by BY-group variable */
proc sort data=Long; by VarName; run;
/* 3. univariate glm regression on single predictor*/
proc glm data=Long outstat=PE;
CLASS Value;
by VarName;
model Y = Value;
ods select FitStatistics;
quit;
proc print data=PE;
run;quit;
/* 3. univariate glm regression on single predictor*/
proc glm data=Long outstat=PE;
CLASS Value;
by VarName;
model Y = Value;
*ods select FitStatistics;
ods output fitstatistics = rSquared parameterEstimates = PE(where=(Parameter='Value'));
quit;
This will capture the data for you in a clean fashion into two data sets rSQuared and PE. You can then merge them to get the table you want. I think for means you'll need a PROC MEANS for mean.
It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.