Message-ID: <68BA555B-AF32-4F88-90C4-783E743B645B@comcast.net>
Date: 2009-11-18T21:42:55Z
From: David Winsemius
Subject: How to choose appropriate linear model? (ANOVA)
In-Reply-To: <2FAA997C-4969-4126-A7F5-2DE384B33539@gmail.com>
On Nov 18, 2009, at 4:06 PM, Steve Lianoglou wrote:
> Hi,
>
> On Nov 18, 2009, at 3:33 PM, Rolf Turner wrote:
>
>>
>> On 19/11/2009, at 9:10 AM, Tal Galili wrote:
>>
>>> Hello Peng,
>>> What you are talking about is "model selection" process.
>>> Although it also sound like you are referring to the more general
>>> subject of
>>> regression model strategies, consider finding this book:
>>> http://www.amazon.com/Regression-Modeling-Strategies-Frank-Harrell/dp/0387952322
>>>
>>> Frank Harrell is a very insightful lecturer, I heard his writing
>>> is also
>>> good.
>>>
>>> I would love to read recommendation from other R members regarding
>>> your
>>> question.
>>
>> Alan Miller's book ``Subset Selection in Regression'' (Chapman and
>> Hall,
>> 1990) has some relevance.
>
> You can also look into the "more recent" approaches, like penalized
> regression. Specifically I'm talking about the lasso or elasticnet.
> Look for the relevant papers by Trevor Hastie and Tibshirani
> (you'll get them from their websites)
>
Just for the record, Harrell's text cites, discusses and endorses
penalized approaches. You can also read his more recent presentation
at his website.
--
David
> Lucky for you, the "glmnet" package is available for R, implements
> both the lasso and the elasticnet, and was written by these same
> people.
>
> -steve
>
> --
> Steve Lianoglou
> Graduate Student: Computational Systems Biology
> | Memorial Sloan-Kettering Cancer Center
> | Weill Medical College of Cornell University
> Contact Info: http://cbio.mskcc.org/~lianos/contact
>
> ______________________________________________
> R-help at r-project.org 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.