Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Comparing weighted and unweighted distributions via Chi2 test


From   Duru <duru80@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Comparing weighted and unweighted distributions via Chi2 test
Date   Thu, 9 Jun 2011 09:52:57 +0200

Thanks Fatih this helps a lot. The problem with pstest is that I dont
have two groups, need to compare weighted and unweighted versions of
the same data set. So for "treated" I need to enter 0=unweighted,
1=weighted, then it gets complicated as there is no such indicator.
Apparently, I will need to keep working with manual calculations after
producing descriptives for unweighted weighted versions.

Best,

Duru

On Thu, Jun 9, 2011 at 1:10 AM, Fatih Unlu <fatih.unlu.misc@gmail.com> wrote:
> I think you might be able to "trick" Stata to take your nonresponse
> weights as if they were created as a result of propensity matching and
> use "pstest" to do the test you have in mind. I would recommend,
> however, considering a more qualitative way of assessing whether using
> nonresponse weights yields substantially different results than not
> using them as the results of these statistical tests would highly
> depend on your sample size (e.g.., in a small sample, you may fail to
> detect substantial differences). For this purpose, you can use
> "standardized differences" or "effect sizes" (see
> http://ies.ed.gov/ncee/wwc/references/idocviewer/Doc.aspx?docId=19&tocId=8
> for more information).
>
> Hope this helps,
>
> Fatih.
>
> On Wed, Jun 8, 2011 at 5:05 PM, Duru <duru80@gmail.com> wrote:
>> Dear all,
>>
>> In order to test if my nonresponse weights change my survey outcomes
>> substantially, I want to conduct Chi2 tests or t-tests between
>> weighted and unweighted distributions/means for a number of variables.
>> Since, I dont know a practical way to do this on Stata, I have to
>> insert weighted and unweighted frequency tables or calculate t-values
>> manually from weighted and unweighted mean and variance estimates. Any
>> ideas on how to do it more easily? (using Stata 10.1)
>>
>> Best,
>>
>> Duru
>>
>> *
>> *   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/
>

*
*   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/


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