I am using the EM method to remedy to Missing Data (first time using this method).

For example, I have a scale that has 16 items (4 items for each of the 4 subscales).

I only want EM to insert a value where at least 80% of items have a valid response.

If a participant has not answered any of the items, I don't want EM to be applied for the missing data.

Does anyone know if there is a way (in SPSS) to set this condition, as currently it replacing all missing data.

Similar questions and discussions