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: Effect size after bootstrapping


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Effect size after bootstrapping
Date   Sun, 4 Sep 2011 12:36:09 +0100

bootstrapping is quantifying uncertainty, not getting a different
estimate of the overall effect. Otherwise put, the overall estimate
would be different only if there were information about its level in
the resamples not present in the complete data, and that isn't so.
Bootstrapping just gives an indication of uncertainty, although
nothing stops you from looking at the distribution of estimates from
the resamples you happen to take; it's merely convention. although a
good one, that many people stop at confidence intervals. However, that
distribution is itself subject to uncertainty, especially in the
tails, unless the sample size is so small that you look at all
possible resamples.

On Sun, Sep 4, 2011 at 11:43 AM, Juan Dominguez
<juan.dominguez@monash.edu> wrote:
> Thanks so much for your prompt answer. However, doesn't each resample
> have different sum of squares and therefore, doesn't the value of eta
> squared differ as well for each resample? Couldn't (or shouldn't) you
> be able to calculate the effect size for each resample to generate a
> distribution of effect sizes and estimate an overall effect size?
>
> Best,
>
> Juan
>
>
> On 26 August 2011 17:15, Maarten Buis <maartenlbuis@gmail.com> wrote:
>> On Fri, Aug 26, 2011 at 7:55 AM, Juan Dominguez wrote:
>>> How can I obtain the effect size (more specifically eta and partial
>>> eta squared) of a bootstrapped regression?
>>
>> Bootstrapping does not affect the effect size, so you can obtain them
>> in the same way as when you did not bootstrap.
>>
>> Hope this helps,
>> Maarten
>>
>> --------------------------
>> Maarten L. Buis
>> Institut fuer Soziologie
>> Universitaet Tuebingen
>> Wilhelmstrasse 36
>> 72074 Tuebingen
>> Germany
>>
>>
>> http://www.maartenbuis.nl
>> --------------------------
>> *
>> *   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