[R] Best way to predict

2012-05-30 Thread Chris Burns
I have a huge matrix of unspecified covariates and the corresponding sales for them. What is the best way to predict the sales from the covariates? Thanks, Chris [[alternative HTML version deleted]] __ R-help@r-project.org mailing list

Re: [R] Best way to predict

2012-05-30 Thread Peter Langfelder
On Wed, May 30, 2012 at 4:07 PM, Chris Burns chris.bur...@gmail.com wrote: I have a huge matrix of unspecified covariates and the corresponding sales for them.  What is the best way to predict the sales from the covariates? Don't want to sound rude, but given your very vague problem

Re: [R] Best way to predict

2012-05-30 Thread Chris Burns
Yea it was meant to be a vague question. I just wanted to see what some of the answers were. It's for a project for school. We've done k nearest neighbors, principal component analysis, partial least squares, and we'll prob throw a random forest in there too. Thanks On Wed, May 30, 2012 at