R help - Apr 2005 - How to know if a classification tree is predicitve or not?

Hello,
I would like to know how to know if a classification tree is predictive or 
not ?
Is it sufficient to analyse results of cross validation?

Thanks for your help
Laure Maton

Laure Maton wrote:
> Hello,
> I would like to know how to know if a classification tree is predictive 
> or not ?
> Is it sufficient to analyse results of cross validation?
Depends on your interpretation of "predictive", maybe you want to look
at stuff like sensitivity and specificity as well.

Uwe Ligges

> Thanks for your help
> Laure Maton
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html

Hello,
I was just thinking about the same question. The
output in CART shows an overal sensitivity and
specificity of the tree built, plus cross-validation
result of overall sens and spec. I find this very
useful for interpretation of the value of a tree.
I didn't find this in the R output?

Greetings,
Ward Schrooten


Message: 5
Date: Fri, 22 Apr 2005 13:04:44 +0200
From: Uwe Ligges <ligges at statistik.uni-dortmund.de>
Subject: Re: [R] How to know if a classification tree
is predicitve or
	not?
To: Laure Maton <maton at toulouse.inra.fr>
Cc: r-help at stat.math.ethz.ch
Message-ID:
<4268DA4C.4070701 at statistik.uni-dortmund.de>
Content-Type: text/plain; charset=us-ascii;
format=flowed

Laure Maton wrote:
> Hello,
> I would like to know how to know if a classification
tree is 
predictive 
> or not ?
> Is it sufficient to analyse results of cross
validation?

Depends on your interpretation of "predictive", maybe
you want to look 
at stuff like sensitivity and specificity as well.

Uwe Ligges

> Thanks for your help
> Laure Maton
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html