s-news
[Top] [All Lists]

fitting a linear model

To: s-news@lists.biostat.wustl.edu
Subject: fitting a linear model
From: Martyn Colins <martyncollins10@yahoo.com>
Date: Fri, 12 Jan 2007 07:43:48 -0800 (PST)
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=xYHqv8wPHxy4+wgBPqNmlkw7YyIzfCvynfTLGgasdIGXxa6bcCDTdcYV8rIPogT2P2PedoknlELDWSBdARSZggnfpN2GOrJbm08QRe5mvQI/2jZmhjq5QyK9gpCKUJ9heaEdeRpnef4ifNZhycasdtLWyMfLJeFuLWzCIErQ7xA=;
Dear members,
 
I would like to fit a linear model using the lm function in the usual way, i.e. y= X*beta + error. However, I have two restrictions on my model. The first is the the sum of the y(i)'s is equal to 1 and the second is the sum of each row in the X matrix is also equal to 1. In the light of these restrictions, is it appropriate to fit a linear model? If not, what type of model should I be fitting?
 
Many thanks in advance for your help.
Regards,
Martyn


No need to miss a message. Get email on-the-go
with Yahoo! Mail for Mobile. Get started.
<Prev in Thread] Current Thread [Next in Thread>
  • fitting a linear model, Martyn Colins <=