Maybe a good startpoint to read and in the future implementing
variance for complex survey is:
MOONEY, C. Z.; DUVAL, R. D. Bootstrapping: a nonparametric approach
to statistical inference. Yowa: Sage Publications. 1993. 73p.
There are replication and linearization methods to estimate variance
for complex survey. You could write a do files that estimate 5 types
of variance for complex survey: (a) Replication: Jackknife, BRR and
Bootstrap; (b)Linearization: Rao e Taylor. For replication methods
there is good sugestion (reference) in:
www.westat.com/wesvar/techpapers/biblio-replication.pdf
If you finish this do file (with 5 kinds of variance) - send to me
and I will put one T-shirt: "Zurab Sajaia is god". Bootstrap for
complex survey (kind AC3) it�s not very easy. Good luck...
--
Patrick Wohrle Guimar�es
(0xx)-21-8646-1444 (celular0 - Oi)
Quotes:
"Um pa�s se faz com homens e livros" (Monteiro Lobato)
"Comece fazendo o que � necess�rio, depois o que � poss�vel e de
repente voc� estar� fazendo o imposs�vel." (S�o Francisco de Assis)
"A vida � a arte de tirar conclus�es suficientes de dados
insuficientes" (Luiz Fernando Ver�ssimo).
*
* 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/
