Hello, I am trying to do some imputation with SAS, and repeated with fixed seed. I tried a simple one. it works.
But when I change the data and codes: 1. x and y are category var while v and w are continuous var; 2 add out=out_data; 3. change imputation method from MCMC to FCS; It did not work.
I am a beginner for MACRO. Could anyone help me for this problem?
Many thanks
/*work*/
data eq;
input y x z w;
cards;
1 23 45 19
0 32 20 .
1 67 . .
1 . . .
;
run;
%macro mi(in_data);
proc mi data = &in_data nimpute=&n_imp seed= &&my_seed&i;
mcmc chain=multiple initial=em(itprint);
var y x z w;
run;
%mend mi;
%macro try(in_data,n_imp,in_seed,n_boot);
data seed_long(drop=i);
call streaminit(&in_seed);
do i = 1 to &n_boot;
x_seed = floor(rand("Uniform")*500000); output;
end;
run;
data _null_;
set seed_long;
call symput('my_seed'|| compress(put(_n_,8.)), x_seed);
run;
%let i=1;
%do %until (&i>&n_boot) ;
%mi(&in_data)
%let i = %eval(&i+1);
%end;
%mend try;
%try(eq,5,123,3)
%put _global_;
/*not work*/
data eq1;
input ID y x z w;
cards;
1 1 23 0 19
2 0 32 1 .
3 1 67 . .
3 1 . 1 3
;
run;
%macro mi(in_data);
proc mi data = &in_data out=out_data nimpute=&n_imp seed= &&my_seed&i;
CLASS y;
FCS REG (x w)
LOGISTIC (y );
VAR y x z w;
run;
%mend mi;
proc genmod data = out_data ;
class ID;
model y = x z w/dist=bin;
repeated subject=ID/type=ind;
by _imputation_;
ods output ParameterEstimates=mvn;
run; quit;
proc mianalyze parms=mvn;
modeleffects x;
ods output ParameterEstimates=sim_y;
run;
%macro try(in_data,n_imp,in_seed,n_boot);
data seed_long(drop=i);
call streaminit(&in_seed);
do i = 1 to &n_boot;
x_seed = floor(rand("Uniform")*500000); output;
end;
run;
data _null_;
set seed_long;
call symput('my_seed'|| compress(put(_n_,8.)), x_seed);
run;
%let i=1;
%do %until (&i>&n_boot) ;
%mi(&in_data)
%let i = %eval(&i+1);
%end;
%mend try;
%try(eq1,5,123,3)
%put _global_;
PROC MI is in SAS/STAT, so it is better to ask in that community.
Registration is open! SAS is returning to Vegas for an AI and analytics experience like no other! Whether you're an executive, manager, end user or SAS partner, SAS Innovate is designed for everyone on your team. Register for just $495 by 12/31/2023.
If you are interested in speaking, there is still time to submit a session idea. More details are posted on the website.
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.