I have a data set on a disease and weight change (sample size=100). Both variables are categorical (disease=Yes/No, weight change= Yes/No). In weight change variable there is 40% missing observation. Data are collected from a hospital's registry book. If I want to find association of weight change with disease using logistic regression what type of imputation is needed for this categorical dependent variable? Could anybody give me any suggestion?

  • $\begingroup$ Do you have any additional information? Such as age, gender, other relevant variables. Without additional information it is hard to make a reasonable imputation. $\endgroup$ – Sheep Oct 21 '15 at 16:33

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.