R help - Mar 2007 - Minimum valid number of observations for rpart

Hi,
I wonder if anyone knows a study dealing with the minimum valid number of
observations when using CART?.
On top of that, when using RandomForest, is it possible to obtained a
interpretable tree model as the graphical output of the analysis, just
like in "rpart"?

Thanks a lot in advance

Javier Lozano
Universidad de Le?n
Spain

On Fri, 30 Mar 2007, fjlozl at unileon.es wrote:
> Hi,
> I wonder if anyone knows a study dealing with the minimum valid number of
> observations when using CART?.
I have no idea what you mean by 'valid' here.
Could you answer the question for logistic regression to indicate to us 
what form of answer you are expecting?
> On top of that, when using RandomForest, is it possible to obtained a
> interpretable tree model as the graphical output of the analysis, just
> like in "rpart"?
By definition randomForest (sic) does not produce a tree but a forest.
> Thanks a lot in advance
>
> Javier Lozano
> Universidad de Le?n
> Spain

-- 
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

Regarding interpretable output, I assume you have looked at the 
  mds plot?  
   
  regards,
  Farrar

fjlozl@unileon.es wrote:
  Hi,
I wonder if anyone knows a study dealing with the minimum valid number of
observations when using CART?.
On top of that, when using RandomForest, is it possible to obtained a
interpretable tree model as the graphical output of the analysis, just
like in "rpart"?

Thanks a lot in advance

Javier Lozano
Universidad de León
Spain

______________________________________________
R-help@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
and provide commented, minimal, self-contained, reproducible code.


	[[alternative HTML version deleted]]