s-news
[Top] [All Lists]

Re: books on non-linear models

To: Unspecifed <dddd@pobox.com>
Subject: Re: books on non-linear models
From: Spencer Graves <spencer.graves@PDF.COM>
Date: Sun, 09 Mar 2003 19:06:50 -0800
Cc: s-news@lists.biostat.wustl.edu
References: <BA92038E.2EEC%dddd@pobox.com>
User-agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.0.2) Gecko/20021120 Netscape/7.01
To my knowledge, the defining works in this area are the following:

Mixed Effects Models in S and S-Plus
by Jose C. Pinheiro, Douglas M. Bates (Hardcover)
Amazon Avg. Customer Rating: 5.0 out of 5 stars

Nonlinear Regression Analysis and Its Applications
by Douglas M. Bates (Author), Donald G. Watts (Author) (Hardcover - August 1988)
Amazon Avg. Customer Rating: 5.0 out of 5 stars

Doug Bates' PhD dissertation over 20 years ago established that the primary problem with nonlinear estimation was "parameter effects curvature". In almost all cases, it is much a much bigger problem than "intrinsic curvature". In "Nonlinear Regression", Bates and Watts show how appropriate reparametization can make nonlinear estimate and the accompanying asymptotic normal theory much more effective and useful.

"Nonlinear Regression" is a seminal contribution to statistical science, and "Mixed Effects Models" is a detailed manual essential for effective use of nlme in S-Plus.

The function "optim" in the MASS library is useful with nonnormally distributed responses.

Hope this helps.
Spencer Graves

Unspecifed wrote:
Dear All,

I am a novice of S-Plus.
Would someone recommend good books on non-linear models using S-Plus.
I want to write programmes for the estimation of non-linear simultaneous
equations by S-Plus.
Thank you in advance.

Harry Wu

--------------------------------------------------------------------
This message was distributed by s-news@lists.biostat.wustl.edu.  To
unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with
the BODY of the message:  unsubscribe s-news



<Prev in Thread] Current Thread [Next in Thread>