Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RES: Need Help with Clusters and Weighting


From   "Henrique Neder" <hdneder@ufu.br>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RES: Need Help with Clusters and Weighting
Date   Thu, 14 Feb 2008 12:49:23 -0300

Liliana

I think that you are dealing with a problem related with the svy commands.
You have a sample that is clustered (and pre-stratified sample). The PSU's
(primary sampling units) are formed by 7 ultimate sample units, each. You
have to generate two new variables in your data base: the strata (a variable
that identify the strata classification of your data) and the psu (the
variable that identify your cluster classification). The weights are the
inverse of your sample fraction (N/n, N = the total of elements in your
population and n = 210). I suppose that you are dealing with clusters in the
population with the same size. So you have a self-weighted sample. 
At first, define the sample design:

svyset psu [pweight=pw], strata || _n

In the sequence you have to execute the svy:logit command

For survey data analysis, a good reference is:
http://www.ats.ucla.edu/stat/stata/topics/Survey.htm

Henrique       


-----Mensagem original-----
De: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Em nome de Rodriguez, Liliana
F
Enviada em: quarta-feira, 13 de fevereiro de 2008 18:08
Para: statalist@hsphsun2.harvard.edu
Assunto: st: Need Help with Clusters and Weighting

I'm working on a project and need to analyze a small dataset (n=210) by
logistic regression (with odds ratios). All of the variables are categorical
or binomial and my outcome is binary Y/N. Data was obtained from 7 samples
in each of 30 clusters. The clusters were soft-stratified in 3 groups
according to income levels.
 
What are the commands to do weighting for the clustering to analyze within a
stratum?
 
What are the commands to do weighting for the strata, and the clustering,
when analyzing over the entire sample?
 
Do I use income levels, crude income, or the population in each cluster as
the weight?
 
Thanks.... I still have a lot to learn.
 
Liliana Rodriguez
Houston, Texas 


*
*   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/

No virus found in this incoming message.
Checked by AVG Free Edition. 
Version: 7.5.516 / Virus Database: 269.20.4/1277 - Release Date: 13/2/2008
20:00
 

No virus found in this outgoing message.
Checked by AVG Free Edition. 
Version: 7.5.516 / Virus Database: 269.20.4/1277 - Release Date: 13/2/2008
20:00
 

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index