Re: [R] Random Forest AUC

2010-10-24 Thread Liaw, Andy
-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Claudia Beleites Sent: Saturday, October 23, 2010 3:39 PM To: r-help@r-project.org Subject: Re: [R] Random Forest AUC Dear List, Just curiosity (disclaimer: I never used random forests till now for more than

Re: [R] Random Forest AUC

2010-10-23 Thread Liaw, Andy
number of iterations. You don't need that with RF. -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of vioravis Sent: Saturday, October 23, 2010 12:15 AM To: r-help@r-project.org Subject: Re: [R] Random Forest AUC Thanks Max

Re: [R] Random Forest AUC

2010-10-23 Thread mxkuhn
the optimal number of iterations. You don't need that with RF. -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of vioravis Sent: Saturday, October 23, 2010 12:15 AM To: r-help@r-project.org Subject: Re: [R] Random Forest AUC Thanks

Re: [R] Random Forest AUC

2010-10-23 Thread Changbin Du
of iterations. You don't need that with RF. -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of vioravis Sent: Saturday, October 23, 2010 12:15 AM To: r-help@r-project.org Subject: Re: [R] Random Forest AUC Thanks Max and Andy

Re: [R] Random Forest AUC

2010-10-23 Thread Claudia Beleites
-project.org Subject: Re: [R] Random Forest AUC Thanks Max and Andy. If the Random Forest is always giving an AUC of 1, isn't it over fitting??? If not, how do you differentiate this from over fitting??? I believe Random forests are claimed to never over fit (from the following link). http

Re: [R] Random Forest AUC

2010-10-22 Thread Max Kuhn
Ravishankar, I used Random Forest with a couple of data sets I had to predict for binary response. In all the cases, the AUC of the training set is coming to be 1. Is this always the case with random forests? Can someone please clarify this? This is pretty typical for this model. I have

Re: [R] Random Forest AUC

2010-10-22 Thread Liaw, Andy
Let me expand on what Max showed. For the most part, performance on training set is meaningless. (That's the case for most algorithms, but especially so for RF.) In the default (and recommended) setting, the trees are grown to the maximum size, which means that quite likely there's only one

Re: [R] Random Forest AUC

2010-10-22 Thread vioravis
Thanks Max and Andy. If the Random Forest is always giving an AUC of 1, isn't it over fitting??? If not, how do you differentiate this from over fitting??? I believe Random forests are claimed to never over fit (from the following link).