I want to do a multiple imputation of missing data using SPSS. I have a nominal (categorical) variable X with missing values codified as '9' and not applicable values codified as '8'.

How can I constrain imputed values to X, for not imputing '8' (not applicable) to a '9' (missing value)?

Since this variable X is categorical it is not possible in SPSS to use 'Define Constraints' for that purpose. Is this possible using other application for multiple imputation (e.g. R)?

  • $\begingroup$ I'm not sure I understand the question. You want SPSS to impute any possible values EXCEPT 8 (not applicable)? You don't want SPSS to impute 8s, is that it? $\endgroup$ – Patrick Coulombe Aug 6 '14 at 16:27
  • $\begingroup$ Yes, I don't want SPSS to impute 8s because 'not applicable' values should be defined in a deterministic way: a missing value cannot be a 'not applicable' by 'chance'. $\endgroup$ – sbac Aug 6 '14 at 16:43

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.