I'm working with NHIS survye data. I'd like the to use muliple imputation to cover the missing data for the variables in which I'm interested. My question concerns the use of certain variables in the imputation model. For example, race would be an important predictor in the imputation model, but it has been imputed (hot deck) as have other variables that might be useful in the imputation model. What is the wisdom of using data that have been imputed in subsequent imputations models?
______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
