A question about Multiple imputations

SD1

New Member
#1
If I use multiple imputations to complete missing values in a certain variable, can I later use the imputated variable in another imputation (to complete missing values in another variable)? If it is possible, how can I do it? when doing the second imputation process should I use the file with the stacked data sets when I enter the varaibles that I want to be included in the analysis and should I just write the name of the imputated variable as it is when I include it?
 

hlsmith

Omega Contributor
#2
This is not may area, but I think you can do this.

My personal question, which I have not done any research on, would you impute independent variables first and what is the strategy (e.g., start with variable missing the least amount of data)?