A0244
Title: Numerical methods for computing optimal regression designs
Authors: Julie Zhou - University of Victoria (Canada) [presenting]
Abstract: Optimal regression design problems on discrete design spaces can be written as convex optimization problems for various optimality criteria. When the number of points in the discrete design space is not very large, several numerical algorithms can find optimal designs effectively. However, when the number of points is huge, say 10,000 or more, it is challenging to find optimal designs. There are also issues with discretizing irregularly shaped design spaces. Recently, an effective iterative procedure is developed to compute approximate optimal designs on discrete design spaces with a huge number of points. This procedure includes several new ideas for computing optimal designs: (1) a new strategy for discretizing design spaces, (2) a new rule for updating design spaces in the iteration, and (3) a new step for clustering support points in optimal designs. It is easy to use and is very fast. It can be applied to any regression model and any convex optimality criterion.
