s-news
[Top] [All Lists]

Re: Regression Trees- Independent Variable Collinearity

To: "Wing, Michael" <Michael.Wing@orst.edu>
Subject: Re: Regression Trees- Independent Variable Collinearity
From: Prof Brian D Ripley <ripley@stats.ox.ac.uk>
Date: Wed, 4 Apr 2001 06:48:02 +0100 (BST)
Cc: <s-news@wubios.wustl.edu>
In-reply-to: <6B677297622ED311A8E100902785F9310302A378@ribes.for.orst.edu>
On Tue, 3 Apr 2001, Wing, Michael wrote:

> Hi all,
>
> To what extent are regression tree (with a single continuous dependent
> variable) results robust in regards to collinearity or correlation between
> independent variables?  I'm interested in this issue when both continuous
> and factor variables are included in the independent variables and also when
> only continuous independent variables are used.

Not at all.  Tree-based methods are not robust to many things, which is
why methods such as bagging and boosting have arisen.  They were designed
to find fairly complex but clear-cut relationships.

-- 
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


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