Re: Searching for Models

Article View: bit.listserv.stat-l

Article #3580

Back to bit.listserv.stat-l Previous Next

#3580

From: HAL
Date: Wed, 29 Jan 1992 19:55

11 lines
1427 bytes

I have been using Bootstrap techniques on stepwise regression analysis of
Principal Components to get around the collinearity problem as well as the
problems mentined on this forum.  Now I am told that Bootstrap methods are
in difficulty and something else should be done.  Is this a real problem or
a method to keep statisticians busy?  I am a dendrochronologist trying to
stay up with statistics but find it hard to stay on top of all of the
current trends.  I was also told that the bootstrap method assums a model
of normality.  I thought it did not assume a particular model because it just
counted the numbers to get the probabilities.   Harold C. Fritts
Laboratory of Tree-Ring Research, Tucson, AZ 85721. Phone 602 887 7291
FRITTS1@ARIZRVAX.BITNET

Technical Details

Message-ID: <01GFW0MLCM3495NQY6@CCIT.ARIZONA.EDU>

Path: arc1-ca.pugleaf.net!sparky!uunet!europa.asd.contel.com!paladin.american.edu!auvm!ARIZRVAX.BITNET!FRITTS1

Show Full Headers

Complete Article Headers

X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: f5efb,e5856ed0bab03434
X-Google-Attributes: gidf5efb,public
X-Google-ArrivalTime: 1992-01-29 12:19:47 PST
Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
Path: arc1-ca.pugleaf.net!sparky!uunet!europa.asd.contel.com!paladin.american.edu!auvm!ARIZRVAX.BITNET!FRITTS1
X-Envelope-to: stat-l@mcgill1.bitnet
X-VMS-To: IN%"stat-l@mcgill1.bitnet"
Message-ID: <01GFW0MLCM3495NQY6@CCIT.ARIZONA.EDU>
Newsgroups: bit.listserv.stat-l
Date:         Wed, 29 Jan 1992 12:55:00 MST
Sender:       "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
From:         HAL <FRITTS1@ARIZRVAX.BITNET>
Subject:      Re: Searching for Models