Dear All, I have an optimization problem of the form: l<=A*p<=u where l and u are vectors of lower and upper bounds, p is a vector of parameters and A a linear constraint matrix. When l=u, it is easy to reparametrize in which case the result is a new set of parameters p' to be optimized. My problem is however that l!=u, ie it is mixed, l and u are equal for a number of constraints and inequal for another set of constraints. If I use the elements where l=u to reparametrize, I would like to know how the inequality constraints translate in new inequality constraints for p', because in that case I could use constrOptim to fit the inequality constraints. Any help appreciated, best, ingmar -- Ingmar Visser Department of Psychology, University of Amsterdam Roetersstraat 15, 1018 WB Amsterdam The Netherlands http://users.fmg.uva.nl/ivisser/ tel: +31-20-5256735