see if this is relevant:
> qui forv i=1/`nclust' {
> cap mrate if v001==`i'
> replace mortrate = $U_1_1
if v001 == `i'
> local cluster = id[`i']
> local mortrate = mortrate[`i']
> post mortrate (`cluster') (`mortrate')
> }
I would be marginally concerned whether -mrate- takes care of the
complex sampling design. It's not in the publicly available through
-findit-, so I cannot check. I am also not quite sure if cluster level
estimates of mortality would make a lot of sense, either... just not
convinced enough for my limited survey statistics background.
I was concerned too. I eliminate clusters with less than 20 households
to meet statistical threshold. But is it sufficient?
Best regards.
Amadou.
--
Stas Kolenikov
http://stas.kolenikov.name
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
