st: Multivariate imputation using STATA

[Munyaradzi Dimairo <mdimairo@gmail.com>]

Dear All

I am setting up a multivariate imputation model using ordered logistic
regression using STATA 11. The model should take into account the
longitudinal nature of the dataset. Does anyone have some knowledge on this?

There is "mi impute ologit" command but this is tailored for a univariate
case and i can't use "mi impute mlogit" because it neglects the ordering
nature of my categorical variables.

Is it also enough to include time in the model to take into account the
hierarchical nature of the data? I know there is some declaration in MLWiN
software about clustering levels of the data but am not sure on how STATA
handles it.


with many thanks

Munya

-- 
Munyaradzi Dimairo
Medical Statistician
Clinical Trials Research Unit
ScHARR (School of Health Related Research)
 University of Sheffield
 30 Regent Street
 Sheffield S1 4DA
 Tel: 0114 (0) 22 25204
 Mobile: +447531421509
 Fax: +44 (0) 114 222 0870
 Email: mdimairo@gmail.com
           m.dimairo@sheffield.ac.uk
           jmdimairo@yahoo.co.uk

http://www.sheffield.ac.uk/ctru/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/