s-news
[Top] [All Lists]

Re: comparing two aov models

To: "Thompson, David (MNR)" <david.thompson@mnr.gov.on.ca>
Subject: Re: comparing two aov models
From: Prof Brian Ripley <ripley@stats.ox.ac.uk>
Date: Thu, 28 Apr 2005 18:32:22 +0100 (BST)
Cc: s-news <s-news@lists.biostat.wustl.edu>
In-reply-to: <327C2434A3DA2D4CB61554D644BAE48BAB3445@LRCPSSMBMXMB001.lrc.ad.gov.on.ca>
References: <327C2434A3DA2D4CB61554D644BAE48BAB3445@LRCPSSMBMXMB001.lrc.ad.gov.on.ca>
On Thu, 28 Apr 2005, Thompson, David (MNR) wrote:

Thank you for the warning Prof Ripley, I will not use anova() as
I originally intended.

However, I am still in need of an answer to the question:

Q1. Do I interpret A lack of significance under F and Chi^2 tests
to indicate that the differences are negligible?

No.  See Statistics 101 for how to interpret a significance test.
`A lack of significance' is merely lack of evidence.

-----Original Message-----
You cannot legitimately apply anova() to two models applied to
different
sets of data.  You do have two sets of data, of different sizes.



--
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 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

<Prev in Thread] Current Thread [Next in Thread>