Customer suggestion and reference:
Provide the ability for PROC MI to perform so-called "jump to reference" multiple imputation.
LaVange, L.M. and Permutt, T. (2016) "A Regulatory Perspective on Missing Data in the Aftermath of the NRC Report", Statistics in Medicine, 25, 2835-2864
That would indeed be very helpful. Plus the ability to provide a variable name that tells PROC MI what to do with each observation (e.g. patient #1 should be imputed under J2R and patient #2 under MAR). That comes up reasonably often (different imputation approaches depending on the reason for why a patient's data are missing). In fact, the well-known 5 macros (https://missingdata.lshtm.ac.uk/2017/04/06/gsk-five-macros/) have a good range of options.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.