D-s-OPTIMAL DESIGNS IN POLYNOMIAL REGRESSION MODELS

In some regression models, our interest is on estimating only some selected parameters instead of all the parameters in the model. D-s -optimality is used for this purpose. We construct D-s -optimal designs for polynomial regression models using a class of multiplicative algorithms, indexed by a function which depends on the derivatives of the criterion function. The function satisfies certain conditions and may depend on a free positive parameter. We also develop strategies for constructing D-s -optimal designs and investigate techniques for improving convergence rates by using the properties of the directional derivatives of the criterion function.