I'm wondering how I should do the following in SPSS.

I have a dataset with missing data (at random). Some values are blank, because the question was "not applicable" to that person (eg. questions about walking asked to people in a wheelchair). I assume I shouldnt want those values filled in with Multiple Imputations. How can I exclude those values?

Thanks in advance

  • $\begingroup$ This seems like a pure-SPSS question rather than one about statistics. If so, it should be asked either on an SPSS list or on StackOverflow. If not, please add more statistical content. $\endgroup$ – Peter Flom - Reinstate Monica Jun 25 '14 at 14:28
  • $\begingroup$ If the real question's "Should I exclude those values ?" or "How do I model those values?" it's a good one for CV - though still needs some context about what you're wanting to do to make it specifically answerable. $\endgroup$ – Scortchi - Reinstate Monica Jun 25 '14 at 14:37
  • $\begingroup$ Thank you both (@PeterFlom en @Scortchi) for you responses. My question is IF i should impute missing data, which isnt randomly missing, but because the question does not apply to the subject. The example is a question "How much pain do you experience when walking" answered by a person in a Wheelchair, so "not applicable". My guts (yes I know..) say, You shouldn't impute this data because the n/a answer is the valid (not missing) answer, but I dont want the n/a answer to be part of the possible anwers after imputation. $\endgroup$ – Justin Jun 25 '14 at 15:42

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.