Statalist


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

RE: st: Jackknifing on Stata


From   jverkuilen <jverkuilen@gc.cuny.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Jackknifing on Stata
Date   Fri, 20 Feb 2009 18:54:41 -0500

@Richard Goldstein: Clusters != delete k jackknife.  

Right, which was why I suggested making artificial clusters, in effect tricking -jackknife- into doing delete k for you.   

-----Original Message-----
From: "Richard Goldstein" <richgold@ix.netcom.com>
To: statalist@hsphsun2.harvard.edu
Sent: 2/20/2009 9:23 AM
Subject: Re: st: Jackknifing on Stata

true, but that is rather different from randomly selecting a group of 
observations to be deleted

Steven Samuels wrote:
> 
> Jay pointed out earlier in the thread that -jackknife- has a cluster 
> delete option.
> 
> -Steve
> 
> On Feb 20, 2009, at 8:56 AM, Richard Goldstein wrote:
> 
>> correct -- to the best of my knowledge, Stata only supports delete-1 
>> jackknife
>>
>> Ric
>>
>> Nick Cox wrote:
>>> OK. I'm thinking back to the original senses. I don't think that Stata
>>> supports that kind of thing directly. Correct? Nick 
>>> n.j.cox@durham.ac.uk -----Original Message-----
>>> From: owner-statalist@hsphsun2.harvard.edu
>>> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Richard
>>> Goldstein
>>> Sent: 20 February 2009 13:43
>>> To: statalist@hsphsun2.harvard.edu
>>> Subject: Re: st: Jackknifing on Stata
>>> nope -- there is actually lots of literature on using grouped, or delete
>>> "d" jackknife
>>> e.g., see, Efron, B. (1982), _The Jackknife, the Bootstrap and other 
>>> resampling plans_, Philadelphia: SIAM (e.g., p. 7)
>>> Efron, B and Tibshirani, R (1993), _An Introduction to the 
>>> Bootstrap_, NY: Chapman and Hall (e.g., p149)
>>> Rich
>>> Nick Cox wrote:
>>>> My understanding of jackknifing is that it is virtually _defined_ as
>>>> leaving each value out in turn and combining all the results to see 
>>>> what that indicates
>>>> about variability. It may be that you want some other cross-validation
>>>> procedure, and well and good, but Stata's jackknifing procedures 
>>>> will not I think
>>>> provide it.
>>>> Nick n.j.cox@durham.ac.uk
*
*   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   |   What's new   |   Site index