Re: About Bootstrap and replacement
- From: "Anon." <bob.ohara@xxxxxxxxxxxxxxxxxxxxxxxxxxxx>
- Date: Wed, 09 Nov 2005 09:52:37 +0200
\"Luis A. Afonso\" wrote:
> It worth to make a pause.
>
> In fact the following question, the starting one, remains without a
> final answer: The mm procedure, that gives practically the same
> results as Bootstrap, could be safely used, or not, by those that are
> reticent to simulate samples with replacement? This is the ONLY
> question I would like to pose. Let´s think about?
>
The problem is that you have to show it has the correct properties (at least asymptotically). Ideally this would mean that it has the same distribution as the actual sampling distribution of the statistic. Sometimes you can get away with just having the same second order properties (i.e. mean and variance being the same).
The reason the bootstrap and jacknife are popular is that they have these properties for a wide range of statistics.
Bob
-- Bob O'Hara
Dept. of Mathematics and Statistics P.O. Box 68 (Gustaf Hällströmin katu 2b) FIN-00014 University of Helsinki Finland
Telephone: +358-9-191 51479 Mobile: +358 50 599 0540 Fax: +358-9-191 51400 WWW: http://www.RNI.Helsinki.FI/~boh/ Journal of Negative Results - EEB: http://www.jnr-eeb.org
.
- References:
- About Bootstrap and replacement
- From: \"Luis A. Afonso\"
- Re: About Bootstrap and replacement
- From: \"Luis A. Afonso\"
- About Bootstrap and replacement
- Prev by Date: Anyone tried Emacs Speaks Statistics
- Next by Date: Re: Anyone tried Emacs Speaks Statistics
- Previous by thread: Re: About Bootstrap and replacement
- Next by thread: Re: About Bootstrap and replacement
- Index(es):
Relevant Pages
|
