This is a mixture model. There are three ways to
treat it:
(1) Ignore one of the variables -- this is not
symmetric
(2) Use a Scheffé model which is symmetric but has
a special form
(2) Use a Cox model with is an ordinary polynomial
model with restrictions on the parameters.
Several statistical programs will make the
calculations, including ECHIP. There is a book by
John Cornell which may help -- I don't think he
treats Cox's model, but I don't remember.
[EMAIL PROTECTED] wrote:
>
> Hello,
>
> A colleague has asked me about what flavor of linear regression to
> use when the explanatory variable(s) are proportions. I know that
> logistic regression handles situations when the *response* variable
> is a proportion, but are there special considerations when the
> explanatory vars are proportions (0 to 1)? I know that such vars
> should be independent, and they cannot all be independent if they
> sum to 1.
>
> I would be grateful for your advice.
>
> -J Dungan
> ~
>
> Sent via Deja.com http://www.deja.com/
> Before you buy.
--
Bob Wheeler --- (Reply to: [EMAIL PROTECTED])
ECHIP, Inc.
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================