1. Combine your first two data steps into one step
2. Format your code so it's legible and comment it as well - This makes it easier to see where steps can be combined.
3. Same with the last set of data steps, combine as many as possible, you may need to re-order the steps. Remember you can rename/add/drop on the SET statement or with PROC DATASETS so if you don't need to process the data do not use a data step.
4. Turn off ODS destinations so that no output is generated and that should save you some more time.
@doreamonjin wrote:
After I run the macro below, it will always take around 20 min to deal with 2 or more independent variables(vlist).
%macro fmreg(dvar=, vlist=, bvar=, inputdata=, outputname=); data FMRegData; set &inputdata; nmiss=nmiss(of &dvar &vlist); keep &dvar &vlist &bvar nmiss mvlag;
data FMRegData; set FMRegData; where nmiss eq 0 ; run;
proc sort data=FMRegData; by &bvar; run;
ods select none; proc glm data=FMRegData; ods output ParameterEstimates=Parm(drop=Dependent Probt Stderr rename=(Parameter=Variable)) fitstatistics=fitstatistics; by &bvar; model &dvar=&vlist / solution; weight mvlag; run; quit;
%WINSORIZE ( INSET=Parm , OUTSET= Parm , SORTVAR= Variable ,VARS= Estimate ,PERC1= 10,TRIM=0);
proc summary data=Parm nway; class Variable; output out=Parm2(drop=_type_ rename=(_freq_=N)) mean(Estimate TValue)=estimates MeanT Std(Estimate)=STD; run; data clus2dstats2(rename=(PARAM=estimates)); set Parm2; tstat=(estimates*sqrt(N-1))/Std; if abs(tstat) ge 1.645 then p='* '; if abs(tstat) ge 1.960 then p='** '; if abs(tstat) ge 2.576 then p='***'; est=put(estimates, 12.7); param=est; PARAM=compress(est||p); drop estimates; run;
data coeff; set clus2dstats2(keep=variable estimates); run;
data tstat(drop=tstat rename=(tstat2=estimates)); set clus2dstats2(keep=variable tstat); tstat2=put(tstat, 12.3); tstat2=compress('('||tstat2||')')/*('('||left(tstat2)||')')*/; run;
proc summary data=fitstatistics nway; output out=FFFit(drop=_type_ _freq_) mean(RSquare)=Result; run;
data FFIT2(keep=Variable Estimates); retain Variable; set FFFIT; Variable='RSQ'; Result=Result*100; nvalue2=put(Result,12.7); estimates=left(nvalue2); run;
data both(rename=(Estimates=Est_&outputname)); set coeff tstat FFIT2; run; proc sort data=both out=both_&outputname; by Variable; run;
%mend fmreg;
... View more
