Using lm to estimate a parameter?

An embedded and charset-unspecified text was scrubbed...
Name: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20130219/c78d5e3f/attachment.pl>
Hi,
I have a data with three variables (X,Y,Z) and I have an equation as
Z=X/(1+L*X/Y) where L is a constant which need to be estimated from data.
How should I write the formula in lm or is it possible to fit a linear
model in this case?
Neither, it is nonlinear in the parameters. See ?nls or ?optim, for example.

Uwe Ligges
Thanks!
Hallen

	[[alternative HTML version deleted]]

______________________________________________
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.

Uwe Ligges <ligges <at> statistik.tu-dortmund.de> writes:
On 19.02.2013 11:23, hellen wrote:
Hi,
I have a data with three variables (X,Y,Z) and I have an equation as
Z=X/(1+L*X/Y) where L is a constant which need to be estimated from data.
How should I write the formula in lm or is it possible to fit a linear
model in this case?
Neither, it is nonlinear in the parameters. See ?nls or ?optim, for example.
Well, if the Z values are not too small, you can linearize it as

    U = (X Y - Y Z) / Z = L X

and solve it with lm(U ~ X - 1), that is without absolute term.
Uwe Ligges

Thanks!
Hallen