I'm wondering what people thing of the mvis and micombine commands available with Stata. The mvis produces a stacked dataset with any number of imputations--10, 20, whatever. The micombine works with many procedures (regress, logit, mlogit, ologit, possion, nib, etc.) and combines they the way norm does.
There is a new version being developed by the author of mvis called ice that will make it very easy to have a different model for each variable being imputed (regress, mlogit, etc.). This seems like a very simple and effective solution and makes doing 20+ imputations effortless. Alan Acock -----Original Message----- From: [email protected] [mailto:[email protected]] On Behalf Of Laaksonen Seppo Sent: Wednesday, June 01, 2005 1:03 AM To: Paul von Hippel; [email protected] Subject: Re:[Impute] fraction of missing information The number of imputations is not most important for me. I am always trying to minimise the bias in point estimates. If I believe that this is successful reasonably, I will continue to estimate the best possible variances (as unbiased as possible, a small overestimate is not not so bad than an underestimate, since it is obvious that our estimate is not completely unbiased). MI does not automatically give any guarantee to the unbiasedness, its 'single basis' should be unbiased. The number of MI-based imputations depends so much on how complex is the variability of the statistic being estimated. In real life the distributions are often complex (skewed, ouliers, etc.). It follows that the number of imputations needs to be higher, 5 or 7 give rarely a satisfactory result. Seppo Paul von Hippel (28.5.2005 1:57): >I'm looking for work that relates the fraction of missing information >(gamma) to other properties of the data -- e.g., the correlation matrix >and the fraction of values that are missing. > >Any references most appreciated. > >Thanks! >Paul > >Paul von Hippel >Department of Sociology / Initiative in Population Research Ohio State >University > > >_______________________________________________ >Impute mailing list >[email protected] >http://lists.utsouthwestern.edu/mailman/listinfo/impute _______________________________________________ Impute mailing list [email protected] http://lists.utsouthwestern.edu/mailman/listinfo/impute
