Running into a strange problem:
I am trying to perform multiple imputation, save the estimates and apply that on a different dataset later.
proc mi data = rest out = rest_mi seed = 1234 nimpute = 5 noprint; mcmc chain = single initial = em outest = storedir.mcmc_est_parms; var f_:; run;
proc mi data = test out = mi noprint; mcmc inest = storedir.mcmc_est_parms; var f_:; run;
When I run both code within the same script one after the other, things work fine.
But when I try to run the second part in a different program I get this message:
WARNING: The INEST= data set has TYPE=, not the required TYPE=EST. INEST= option will not be used. WARNING: The default number of imputations has been changed from 5 to 25.
Any thoughts would be appreciated
As a work-around, you might consider reading mcmc_est_parms into the WORK library, and then hardcoding from TYPE= to TYPE=EST. Without seeing that particular dataset, I can't say for sure what might be happening that would make the out= option lead to the behavior you mention.
SteveDenham
I suspect that you have accidentally changed the data set before you use it again as it should have no bearing on whether you use it right away or not.
I would run a Proc CONTENTS right before the distant MI call to find out what is going on with the data set type. You could set it to TYPE=EST as someone else suggested previously.
ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.
Find more tutorials on the SAS Users YouTube channel.