Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: R: Jackknife bias and standard errors


From   "Carlo Lazzaro" <carlo.lazzaro@tin.it>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: R: Jackknife bias and standard errors
Date   Sat, 9 Feb 2008 12:09:32 +0100

Dear Daniel,
about your questions:

- the bad news: as far as I am concerned, there's no way to obtain from
Stata the bias equation 11.3 mentioned in Efron B, Tibshirani RJ. An
Introduction to the bootstrap. New York: Chapman & Hall, 1993: p. 141 (BTW:
I would strongly recommend you to report the full reference of the
articles/texts supporting your analysis, since Statalisters are from far
different professional/academic clusters: this will probably increase your
reply score);

- the good news: you can obtain directly from Stata the jackknife standard
error estimate, according to the equation 11.5 reported in the same page of
the abovementioned textbook (please, see example below):
****************************************************************************
sysuse auto.dta
sum  mpg
return list
scalar mean=r(mean)
jackknife r(mean), nodots saving(C:\Documents and
Settings\carlo\Documenti\Statistiche\Stata\jackknife.dta, every(1) double
replace) verbose : sum  mpg
****************************************************************************
Eventually, two more advice may sound useful: 
take a look to Stata manual Reference A-J (I refer to Stata 9 release) and
see the examples for -jackknife- (however, I suppose that you have already
scan these pages);
-why don't you consider to switch to bootstrap from jacknife? In Efron &
Tibshirani textbook (pag. 145-146) there is an interesting paragraph (11.5)
explaining pros and cons of both these approaches.

HTH and Kind Regards,

Carlo
-----Messaggio originale-----
Da: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di daniel cassar
Inviato: venerdě 8 febbraio 2008 20.26
A: statalist@hsphsun2.harvard.edu
Oggetto: st: Jackknife bias and standard errors

Hi,

I am new doing Jackknife analysis. I am following Efron and Tibshirani
(1993) and want to obtain the bias (equation 11.3 in the aforementioned
book) and standard error (eq. 11.5). How do I get these with stata? Is it
just a matter of using -jackknife- . 
Also, what is the best way of reporting them?

Best regards, 
DC




 
____________________________________________________________________________
________
ˇCapacidad ilimitada de almacenamiento en tu correo!
No te preocupes más por el espacio de tu cuenta con Correo Yahoo!:

http://correo.espanol.yahoo.com/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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