B1266
Title: Optimal designs for fractional polynomial models
Authors: Victor Casero-Alonso - University of Castilla-La Mancha (Spain) [presenting]
Jesus Lopez-Fidalgo - University of Navarra (Spain)
Chiara Tommasi - University of Milan (Italy)
WengKee Wong - UCLA (United States)
Abstract: The aim is to show design issues for Fractional Polynomials (FP) models. We have constructed D- and I-optimal designs for estimating model parameters and prediction in FP models with a single factor, and we have developed an applet to facilitate users in finding various types of tailor-made optimal designs for their problems. We have considered three studies that used experimental design to model risk assessments fitted by FP models, to illustrate the usefulness of the optimal experimental design. Furthermore, there is interest in obtaining KL-optimal designs to discriminate between two FP models, even among several FP models. Algorithms are needed to achieve that goal. We have adapted the nature-inspired Particle Swarm Optimization algorithm to obtain such designs