Clear Imputations

[Senor Edward]

Hi,
I'm wondering whether there is any way to remove the imputations from the dataset after I'm finished with them.
i.e.
mi set wide
mi register imputed marriage_Stat
mi register regular age sex cancer_Found
mi impute chained (mlogit) marriage_Stat = age sex cancer_Found, add(10) rseed augment
mi estimate: logit cancer_Found age i.sex i.marriage_Stat

and now that I am finished with the analysis, I want to drop these imputed values and create a new imputation for another model.
This idea is described in this thread as well, but no solution found.

http://www.stata.com/statalist/archi.../msg00386.html

Is there any line of code to clear the imputed values?
I was thinking of manually dropping the variables/values, but this seems rigid and I assume someone would have already thought of this and created a better solution.

[Clyde Schechter]

mi extract 0

But given that the imputations are so time consuming to produce, I would recommend saving the data (including the imputations) somewhere and then starting over. You might need them again.

[Rich Goldstein]

I agree with Clyde but would give slightly different advice for the future; just before you enter your -mi- commands, make sure you have saved your data file; after you have imputed, save the file under a different name