[R] different models

From: Stephen Choularton <mail_at_bymouth.com>
Date: Wed 28 Sep 2005 - 08:17:21 EST


I have a largish dataset (26 columns 35000 rows) which I have been subjecting to logistic regression and support vector machine analysis. I have noticed that R easily copes with using the data in either technique. Now I have to try and see what the best modeling technique to use is.  

I only have limited time (who doesn’t) so I thought it would be best to try the data with any other techniques on R that can handle that data set and then use predict() and so on. I have identified the following techniques (you may know of more) and think the packages indicated will support them:  

Neural networks             ->         AMORE
Genetic/evolutionary       ->         ?
Bayes                           ->         deal
Decision trees               ->         knnTree
Gaussian processes      ->         predict

Are these the right packages where I can go model = etc, predict(model,etc using my dataset?  

Have I missed some techniques?  

Does anyone know the package I couldn’t find for genetic.  

All help/comments welcome.  





	[[alternative HTML version deleted]]

______________________________________________ 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

Received on Wed Sep 28 08:21:10 2005

This archive was generated by hypermail 2.1.8 : Sun 23 Oct 2005 - 17:50:31 EST