05-03-2018 01:18 PM
I am trying to do multiple imputation, by treatment group.
i am running the following code:
proc MI data= raw seed=46485 nimpute=5 out= temp ;
class trt01p ;
var trt01p base month1 month3 ;
monotone reg (month3 = base month1/details) discrim( trt01p /classeffects = include ) ;
the log always came up with a warning message:
WARNING: The imputed variable TRT01P in the MONOTONE statement is the leading variable in the VAR list. Missing values for this
variable will not be imputed.
What is the issue here? should I use 'by treatment' other than 'class treatment', and also do not include treatment in the var list and monmontone statement?
Thanks very much
05-08-2018 08:00 AM
By the nature of how montone models work, you will not be able to impute the first variable in the list because there are no variables prior to it that can be used in its imputation model.
That being said, you might consider, if you have missing values in the first variable, using the FCS method instead.