How can SPSS recognize a dataset from another package as imputed

[abcdefghij]

I have imputed my data, which is multilevel, on Mplus and combined all the iterations to form a dataset and transferred to SPSS.
but I am not sure how to make SPSS recognize this dataset as imputed with multiple iterations.
I have tried splitting the file, but the problem is I cant get a pooled analysis of the results from all imputations this way.
anyone got an idea how I can beat this one?

 

[hlsmith]

I haven't used SPSS much, but traditionally what I have done is, say use multiple imputation (m=10), then marked each imputed set with a numeric value (e.g., 1-10). So all observations within an imputed set has the same variable value, example variable name Impute value = 1 if in the first set. Then when pulling or performing other functions, I just reference the variable "Impute" as a strata variable. Not sure why you are unable to do this in SPSS.

 

[abcdefghij]

I haven't used SPSS much, but traditionally what I have done is, say use multiple imputation (m=10), then marked each imputed set with a numeric value (e.g., 1-10). So all observations within an imputed set has the same variable value, example variable name Impute value = 1 if in the first set. Then when pulling or performing other functions, I just reference the variable "Impute" as a strata variable. Not sure why you are unable to do this in SPSS.

Hi hlsmith.
Many thanks for your response. I have already computed a new variable on 'imputation' which I have used to mark each imputed set from 0 to 5 (m=5), with 0 for the original dataset with missingness. I referenced the variable 'imputation' as a strata variable and even split the merged dataset based on the 'imputation variable'.
The persistent issue is that when I run an analysis, it produces output for each of the 6 sets (5ms and 1 original), but not a pool of the results from these 6 sets.

 

[abcdefghij]

Hi hlsmith. thanks for your earlier comment. I sorted this out by adding an underscore to the variable label 'imputation'.
Apparently, adding a variable with the label 'imputation_' makes SPSS recognize the dataset as having imputed iterations.

 

[hlsmith]

Great. Yes, it is great if the program can run the pooling process. Otherwise if I remember correctly, pooling by hand is easy enough, but getting the standard errors is a little more difficult by hand.