st: Inverse probability of treatment weights

[David Torres <torresd@umich.edu>]

I've read Fewell et al.  
(http://www.hsph.harvard.edu/causal/software/fewell_stataj04.pdf) on  
the construction of inverse probability of treatment weights, but  
wonder whether i have things correct.
It looks like I have to create stabilized and censoring weights on my  
longitudinal data, but I'm not sure what predictors should be in the  
logistic model.  Any tips?
My outcome for the stabilized weights is whether a respondent was  
interviewed (0=no 1=yes).  For the censoring weight, the outcome is of  
course whether the respondent was not followed up (1=censored 0=not  
censored).  My data are in long format.  Do these sound like the right  
outcomes?
Diego

--
David Diego Torres, MA(Sociology)
PhD Candidate in Sociology

2044 Population Studies Center
University of Michigan Institute for Social Research
Ann Arbor MI  48106-1248
Tel 734.763.4098
Fax 734.763.1428
torresd at umich dot edu




*
*   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/