[R] choosing constraints for function optim method="L-BFGS-B" when they are in terms of other parameter values

[Prof Brian Ripley]

Basically, you can't as L-BFGS-B implements box constraints and you don't 
have a box.

You could run a nested optimization, the inner one being over the two 
variables that you want to upper-bound.  Contact me offline if that is not 
clear to you.

On Mon, 26 Jul 2004, Tom Stone wrote:

> I have a function of several variables which I wish to minimise over four
> variables, two of the upper bounds for which are defined in terms of other
> variables in the model over which minimisation will take place. I cannot
> work out how to code this in such a way as to avoid getting an error message
> when I run the code.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595