How to apply post-stratification weights in STATA

[Carolina Garza]

Hello everyone,

I am working with a dataset that provides the post-stratification weight for each observation, the issue is that I don't know how to tell Stata to use it every time I run a regression, summary statistics, etc.

Does anyone know how I can do this?

I really appreciate your help!!

Thank you.

Best regards

[Nick Cox]

The question is puzzling. Most statistical commands let you specify weights. See for example the help on commands such as regress or summarize.

[Carlo Lazzaro]

I do hope that Steve Samuels comes across this thread and decide to come back to the list!

[Carolina Garza]

Actually, I've just read an old thread of Steven Samuels that discusses post-stratification weights

In this thread http://www.stata.com/statalist/archi.../msg00647.html he specifies:

"In any case, the -svyset- statement will be: > > ******************************** > svyset _n [pw = supplied_weight] > ******************************** > > where you should substitute the name of the supplied weight variable after the equal sign. > > You can then commands such as -svy: mean-, -svy: tab-, and -svy: logistic- for your analysis."


However, I am realizing that -svy has a limited number of commands that can be used, which do not include the commands I need, therefore whenever I specify a command I include [pweight=supplied_weight]

for example: xi: reg y x1 x2 x3 i.x4 i.x5 [pweight=supplied_weight]

does this make sense?

Thank you for your help.

Best regards,

[Carlo Lazzaro]

Carolina:
have you already taken a look at -poststratification- entry in Stata .pdf manual?

[Carolina Garza]

Carlo,

Yes I've read it, however my dataset is a survey that does not provide data for poststrata nor for postweight. It just provides an already defined post-stratification weight for each observation based on the population characteristics such as age distribution, gender, region, etc.

Thanks for your help.

Best regards,
Carolina

[Carlo Lazzaro]

Carolina:
it seems a sort of black-box, then.
Sorry I cannot be more helpful.
Will Steve Samuels ever chime in?

[Sara Angheben]

Hello! I am having a similar issue, since my dataset only provides the post-stratification weights.
Were you able to solve it?