I am attempting to use multiple imputation on a categorical variable with 8 categories.  Half of the cases are in one category and the other half are spread evenly among the other 7 categories.  5% of the values on this variable were randomly deleted.  The other variable in the model is also categorical with two values..80% are 1 and 20% are 0.   

The imputation did not work:  no cases were imputed.  There was a warning that "Some missing values cannot be imputed because a factor in the model has a value that does not appear in the data used to build the model."  I realize that sometimes this warning is a false alarm but not here.  The imputation did not work.

Attachment(s)

Screenshots of selected options for the multiple imputati...doc   744 KB 1 version