one place to start is with
Rabe-Hesketh, S and Skrondal, A (2006), "Multilevel modelling of complex
survey data", _Journal of the Royal Statistical Society, Series A_,
169(4): 805-827; their examples use -gllamm- which is downloadable via ssc
Rich
Hillel Alpert wrote:
> Has anyone experience with multilevel modeling of survey data with strata and weights?
>
> The prospective analysis will examine country-level effects in addition to individual effects on a binary outcome. Within countries, the survey responses are stratified by school and class and weighted for unequal selection probabilities. So the data include country, stratum, psu, and weight variables.
>
> Could anyone describe or provide an example of the command to use and syntax, how to assign levels and the weight variable (eg. using xtmelogit or more appropriate command)?
>
> Hillel Alpert
*
* 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/
