oslo <hokut1@YAHOO.COM> wrote
>
>I have data from molecular study (SNPs data). data set has 35000 columns and I have some missing data to be imputed. However I figured out from SAS documantaton that PROC MI is OK for�  rilmultivariate data (For data sets with arbitrary missing patterns, a Markov Chain Monte Carlo (MCMC) method (Schafer 1997) that assumes multivariate normality is used to impute all missing values or just enough missing values to make the imputed data sets have monotone missing patterns)
>
>Still can I use PROC MI to impute for my data?
>

Do you have monotone missing data?

If so, you can use other methods, designed for non-normal data.  If not, then you have to compromise somehow

Peter

Peter L. Flom, PhD
Statistical Consultant
Website: http://www DOT statisticalanalysisconsulting DOT com/
Writing; http://www.associatedcontent.com/user/582880/peter_flom.html
Twitter:   @peterflom