Statalist


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

Re: st: RE: ice, mim & bootstrap


From   "Stas Kolenikov" <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: ice, mim & bootstrap
Date   Tue, 9 Dec 2008 15:33:00 -0600

I replied to a similar question a few weeks ago, and to my mind, a
better order is to impute and regress within each bootstrap sample. At
least that's the preferred order for complex survey bootstrap... and I
doubt that educational data have structure simpler than students
nested in schools :))

On 12/9/08, Nick Cox <n.j.cox@durham.ac.uk> wrote:
> It means what it says. This is asking (a) too much (b) the wrong thing.
>  You should impute first, then -bootstrap-. All caveats one can think of,
>  and more, no doubt apply.
>
>  Nick
>  n.j.cox@durham.ac.uk
>
>  Xu, Haiyong
>
>  Could somebody let me know if I can use mim to combine the bootstrap
>  results using the imputed data? When I was running the following codes,
>
>  mim, noi: bootstrap: regress science ses female math
>
>  It gives me an error message of "prefix bootstrap not allowed after
>  mim".
>
>  *
>  *   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/
>


-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
*   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   |   What's new   |   Site index