I am trying to optimize a likelihood function using constrOptim. I
know from prior research that, e.g. x1x2. Is there a way to include
that constraint into the optimization routine, i.e. the ci
constraint? The examples I found only use absolute numeric values for
the constraint and not
Reparameterize replacing x1 with x2+delta constraining delta
to be positive or else replace x1 with x2 + delta^2 and
no constraint.
On 10/6/06, Felix Eggers [EMAIL PROTECTED] wrote:
I am trying to optimize a likelihood function using constrOptim. I
know from prior research that, e.g. x1x2. Is