Dear James,
While waiting for more knowledgeable answers, I can address your first question:
> 1) In a simple bivariate analysis, I want to compare the prevalences of
> chronic medical conditions in each data set. But how can I tell Stata to use
> one set of survey parameters for cases in the NCS-R and another for cases in
> my local data set?
You can combine strata from both surveys in the same strata variable
that will be used when svysetting; just make sure the codes for strata
from different surveys do not overlap. You can combine PSU codes in
the same fashion, just making sure numbers or names of PSUs from both
surveys are not repeated. Weights can be combined in the same variable
without further consideration.
> Also, how important is it to control for a finite
> population correction factor? I have not done this in any analyses
> previously.
See this message: http://www.stata.com/statalist/archive/2009-02/msg00806.html
Best regards,
Angel Rodriguez-Laso
2010/2/14 James Swartz <[email protected]>:
> All,
>
> I searched for information on this topic and found a bit in archived
> threads, but not as much detail as I need. So at the risk of some
> redundancy, I would like to ask for help from a sampling statistician out
> there who also knows Stata well and who has worked with multiple survey data
> sets:
>
> I am using two data sets. One is the National Comorbidity Survey Replication
> (NCS-R) and the other is a data set based on data I collected locally using
> the same instrument as the NCS-R. The N's are very different: the NCS-R part
> 2 is around 5,000 to 6,000 cases and my data set has only about 450 cases.
> Each data set has different survey parameters. I have no PSUs but do have
> stratification on gender and I developed weights to account for non-coverage
> and non-response. The NCS-R data set includes variables for weights, strata,
> and PSUs. Here are my questions:
>
> 1) In a simple bivariate analysis, I want to compare the prevalences of
> chronic medical conditions in each data set. But how can I tell Stata to use
> one set of survey parameters for cases in the NCS-R and another for cases in
> my local data set? Also, how important is it to control for a finite
> population correction factor? I have not done this in any analyses
> previously.
>
> 2) In a second step, I used the PSMATCH2 add-on to create a matched sample
> of 450 cases from the NCS-R data set based on a selected set of demographics
> and other characteristics. I then want to fun logistic regressions on the
> odds of having a chronic medical conditions while controlling for the
> matching variables (the matches were not perfect) and other unmatched
> characteristics. I assume that at this point, the survey parameters are not
> applicable because there is no way (that I can figure) to apply the
> subpopulation option. Is that correct? Is this analytic model reasonable
> given the data sets available or would there be a better way to approach
> this problem?
>
> Thanks for any help. I have been scratching my head on this one for awhile.
>
> James
>
> --
>
> James Swartz, Ph.D., Associate Professor
> Jane Addams College of Social Work, University of Illinois at Chicago
> 1040 W. Harrison Street (MC 309)
> Chicago IL. 60607
>
> http://www.uic.edu/jaddams/college/subabuse/
>
> P 312-996-8560
> F 312-996-2770
> C 312-961-3843
>
> E (W): [email protected]
> E (H): [email protected]
>
> "That which stands in the way of our work, is our work."
> - Marcus Aurelius
>
> *
> * 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/
>
*
* 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/
