Skip to content
Back to formatted view

Raw Message

Message-ID: <Pine.LNX.4.61.0505101421240.12508@gannet.stats>
Date: 2005-05-10T13:23:06Z
From: Brian Ripley
Subject: question about k in step
In-Reply-To: <20050509091037.25f07d90@localhost.localdomain>

On Mon, 9 May 2005, ronggui wrote:

>> ?step
> ....
> 'step' uses 'add1' and 'drop1' repeatedly; it will work for any
>     method for which they work, and that is determined by having a
>     valid method for 'extractAIC'. When the additive constant can be
>     chosen so that AIC is equal to Mallows' Cp, this is done and the
>     tables are labelled appropriately.
>
> so my question is :what constant should i choose so i can get Mallows' 
> Cp instead of AIC?

k=2, that is AIC.  Under some circumstances Cp = AIC+const (as it says), 
and then the const is chosen so that AIC (which is only determined up to a 
const) is equal to Cp (which is defined exactly, at least by Mallows).

-- 
Brian D. Ripley,                  ripley at 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