[19106] in s-news-athena
Re: [S] Confsed with step.glm
daemon@ATHENA.MIT.EDU (Prof Brian Ripley)
Fri Sep 3 11:27:35 1999
Message-Id: <199909031521.QAA10599@toucan.stats.ox.ac.uk>
Date: Fri, 3 Sep 1999 16:21:56 +0100 (BST)
From: Prof Brian Ripley <ripley@stats.ox.ac.uk>
Reply-To: Prof Brian Ripley <ripley@stats.ox.ac.uk>
To: Gerald.Jean@spgdag.ca
Cc: s-news@wubios.wustl.edu
Mime-Version: 1.0
Content-Type: TEXT/plain; charset=ISO-8859-1
Content-Md5: Y006CZKuLpdy+vj4um4IMA==
Content-Transfer-Encoding: 8bit
From: "Gérald Jean" <Gerald.Jean@spgdag.ca>
[Stepwise fits in glms]
> What is going on? Why is that variable not significant according to t-test
> but very highly significant according to all other tests????
It is known that this can happen: there is a paper by Hauck & Donner
(JASA 1977). A small t ratio means EITHER insignificant OR very
significant. See V&R2 p.237 for a more detailed explanation (than this
one). That is one reason why step.glm, which relies on local
linearization, can be almost infinitely misleadingly. It is why I
originally wrote stepAIC (in library MASS), to calculate the real AIC
for glms (and other things)
--
Brian D. Ripley, ripley@stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272860 (secr)
Oxford OX1 3TG, UK Fax: +44 1865 272595
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
