Have you looked at the detailed documentation available here?
http://gking.harvard.edu/zelig/docs/normal.survey.pdf
Kosuke
--
Department of Politics
Princeton University
http://imai.princeton.edu
On Wed, 30 Sep 2009, Fabr?cio Mendes Fialho wrote:
Hi Zelig developers and users,
I am working with complex survey data; dataset is representative of a
Brazilian metropolitan data. Sample is based on a three-level
sampling: in the first stage, census tracts (CT) from the metropolitan
area were randomly selected (with chances proportional to size); then,
households were chosen from every previously selected census tract;
finally, a respondent was randomly chosen from the adult members of
the household. Initial sample design was designed for 1,270 cases, and
the total of successfully completed interviews was 1,029. (survey
response = 81%. not bad!)
Dataset I am analyzing includes (1) post-stratification weights (to
adjust proportionality due to survey non-response), (2) an ?expansion
factor? (a weight that equals the sample to the population, that is,
it says approximately how many people in the population are
represented in each sample case), and (3) census tract (indicating
from which census tract each case was selected).
Due to sample design, we have several cases from the same census
tracts (99.9% of CTs provided from 5 to 20 cases; just one CT provided
only one case). This way, it seems that the most appropriated
regression models to analyze data from this sample might be the
?.survey? ones (logit.survey, normal.survey, etc).
All that explained, my question is: supposing a survey-weighted normal
model like
z.out <- zelig(Y ~ X1 + X2, model = "normal.survey", data = mydata)
which information from survey design should I include? My first
impression is that post-stratification weights (PSW) would correspond
to ?weights? input, the Census Tracts number would correspond to ?ids?
(since CTs are cluster from which each information was drawn). Can I
include these two information in the same regression, obtaining
something like
z.out <- zelig(Y ~ X1 + X2, model = "normal.survey", ids = ~CT,
weights = ~PSW, data = mydata)?
Or can I include only one survey design information in a model? Or
should I use other configuration?
Thanks for all help,
Fabricio M. Fialho
-
Zelig Mailing List, served by Harvard-MIT Data Center
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options:
http://lists.gking.harvard.edu/?info=zelig
Zelig program information:
http://gking.harvard.edu/zelig/