Re: st: pweight question

["Michael I. Lichter" <mlichter@buffalo.edu>]

Steve,

That does sound like a pweight, and if you know nothing else about the 
survey, you should treat it as a pweight.

The scale of the weights (what they sum to) doesn't tell you whether or 
not they are pweights. Scaling the variables to sum to the size of the 
sample is something you do when you expect to use a package (or command) 
that, like SPSS until recently, only accepts fweights.

Do you have any additional information about the design of the study? 
Are there any design variables (strata, clustering variables) in the 
dataset?

-ml

Steven Archambault wrote:
> Hi all,
>
> I have some meta data from a survey that says "A weight was calculated
> based on the probability that the observation would be included in the
> sample." It sounds like a probability weight. However, when I add up
> all of the values in the corresponding weights column in the data, the
> total is equal to the total number of observations. So, it seems like
> these weights are more about how the observations are represented in
> the sample. Does anybody have a suggestion as to what I should do with
> this weight data? These are households in a cross country survey.
>
> Thanks,
> Steve
> *
> *   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/
>   

--
Michael I. Lichter, Ph.D. <mlichter@buffalo.edu>
Research Assistant Professor & NRSA Fellow
UB Department of Family Medicine / Primary Care Research Institute
UB Clinical Center, 462 Grider Street, Buffalo, NY 14215
Office: CC 126 / Phone: 716-898-4751 / FAX: 716-898-3536

*
*   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/