Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: How to apply -bootstrap- but use -fweight- in -summarize- or -regress-?


From   Steve Samuels <[email protected]>
To   [email protected]
Subject   Re: st: How to apply -bootstrap- but use -fweight- in -summarize- or -regress-?
Date   Mon, 19 Apr 2010 11:07:52 -0400

Treating your weights as  -fweights-  will give entirely wrong
standard errors: To Stata, an fweight denotes the number of copies of
the observation in the _sample_, not in the _population_.  I think
your weights are pweights.

Without knowing anything about the study design or your intended
analyses, it's difficult to give further advice. For bootstrapping
weighted survey (and other) data,  see:
http://ideas.repec.org/p/boc/nsug08/19.html  by Stas  Kolenikov

Steve


On Mon, Apr 19, 2010 at 2:48 AM, Misha Spisok <[email protected]> wrote:
> Hello, Statalist!
>
> I can't figure out how to get around -bootstrap-'s inability to apply
> weights.  I'd like to do something like the following (assuming it's
> correct, in principle):
>
> bootstrap me_se=r(sd): sum me [fweight=number]
> bootstrap me_se=e(b): reg me [fweight=number]
>
> where 'me' is a statistic for which I am trying to get a standard error.
>
> Data look something like below, with 'me' being the statistic and
> 'number' being the number of times that value is repeated in the
> population.  The actual sum of 'number' is over 100,000,000.
>
> me                                number
> 0.004656171     411
> 0.000921952     256
> 0.00332348      677
> 0.003846806     875
> 0.005841959     815
> 0.008070664     717
> 0.000966846     780
> 0.004082443     403
> 0.00874068      546
> 0.004901177     925
> 0.004868469     87
> 0.008825776     346
> 0.006638993     432
> 0.009060225     325
> 0.007342354     999
> 0.007714793     28
> 0.006781056     332
> 0.002377917     341
> 0.009975764     137
>
> Thank you for taking the time to read this.
>
> Best,
>
> Misha
> *
> *   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/
>



-- 
Steven Samuels
[email protected]
18 Cantine's Island
Saugerties NY 12477
USA
Voice: 845-246-0774
Fax:    206-202-4783

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index