Hello,
I'm trying to run multiple imputation on SPSS 25 with defined constraints, and am getting the following warning that stops the execution of the process:
"After 100 draws, the imputation algorithm cannot find an imputed value under the constraints for variable XXX. Check the minimum and maximum values specified to determine that they are reasonable, and consider raising the number of draws allowed."
I've checked the min and max values and raised the number of draws, but am still getting the same error with the same or different variable.
The thing is that if I don't define constraints, let SPSS "figure out" min and max itself, SPSS imputes out of the range values. Let's say if min and max for the variable is 1 and 5, imputations can be 0.4 or 6.2.
Thank you!
Shirin
Hello,
Have you tried to increase the number of imputations from 11?
Also, you could consider the non-constrained answer to be constrained and just alter the estimates to fit the appropriate values for a particular variable. In other words, if the min=1 and max=5 and the imputed values are min=0.4 and 6.2 you know these values aren't possible but you could tinker with the idea that 0.4 (or anything 5.0 (6.2 for example) is 5.
Then see if the altered imputed values are not statistically significantly different than the non-imputed values (I would use some type of propensity score for matching the imputed vs. non-imputed values). If they are not significantly different from each other after matching, then it seems like imputed values would be acceptable.
This is not a definitive way to address the issue you are facing; however, I would give it a shot and see what happens.
If someone posts a more conventional or appropriate method for dealing with the issue I would probably go ahead and take that route, but I figured I would just give a suggestion.
Logan Netzer
Thank you, Logan, for taking time and responding to my question. Your suggestion makes total sense, and I think it is a good one. The hard thing about it is that I'll need to recode all variables that are < 1 into 1 and anything >5 into 5. It might be time consuming, but certainly doable.
On another forum, somebody told me that the reason why SPSS gives out-of-range values during multiple imputation is because my data is possibly skewed. He was right, my data was skewed. One way to deal with it is to impute data after data transformation.
Once again, thank you.
Warmly,
Shirin
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS