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: Resampling and compare full sample with subsamples
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Resampling and compare full sample with subsamples
Date
Fri, 7 Mar 2014 10:57:40 +0000
The Stata Journal site seems to be down at the moment.
Nick
[email protected]
On 7 March 2014 10:41, Johannes Thrul <[email protected]> wrote:
> Thank you Maarten!
>
> This last link you sent does not seem to work for me, can you please resend it or tell me which article it is so I can look for it myself?
>
> Thanks, Johannes
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected] [mailto:[email protected]] Im Auftrag von Maarten Buis
> Gesendet: Freitag, 7. März 2014 11:31
> An: [email protected]
> Betreff: Re: st: Resampling and compare full sample with subsamples
>
> That is in essence a simulation study to get an idea of what missing observations does to your data. I will start with the bad news: the problem is well studied so I doubt it will give you insights beyond what is already known, so I would not expect to gain anything "publishable" from such an excercise.
>
> Having said that, creating simulations is still a fine strategy to get a grip on such a problem, and can thus be a good supplement (but not a
> replacement) to reading on this subject. There is a difference between reading that purely random missingness will (on average) not impact your estimates other than having less data and seeing it happen in your own simulation. There are a number of tools available for running and displaying simulations in stata:
>
> http://www.maartenbuis.nl/presentations/chicago08.html
>
> http://www.maartenbuis.nl/presentations/gsug13.pdf
>
> http://www.stata-journal.com/article.html?article=st0200
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/