Message-ID: <Pine.LNX.4.64.0809031156290.23054@paninaro.stat-math.wu-wien.ac.at>
Date: 2008-09-03T10:03:24Z
From: Achim Zeileis
Subject: Oblique decision tree using mvpart
In-Reply-To: <19285410.post@talk.nabble.com>
On Wed, 3 Sep 2008, Clusty wrote:
> I want to try oblique decision tree. I have found the mvpart package. In the
What gave you the idea that mvpart was an implementation of oblique
decision trees? It does not say so anywhere.
> help file, there is an example of the mvpart function using the spider data
> set. However, when trying the example I do not obtain an oblique decision
> tree with separating rules such as p1+p2<5, but rather simple rules of the
> form p1>3. Is it normal?
Yes. As the task view that I pointed you previously explains
An adaptation of rpart for multivariate responses is available in
package mvpart.
Thus, this is for multivariate *responses*, not for multivariate splits.
Z
> Thanks for your replies.
> Sandro.
> --
> View this message in context: http://www.nabble.com/Oblique-decision-tree-using-mvpart-tp19285410p19285410.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>