Jie Yang : Analytic solutions for D-optimal factorial designs under generalized linear models

Posted by Roman Shvydkoy , part of the MATH Club.

At

March 7, 2018, 5 p.m.

In

seo 300

Abstract

In order to find D-optimal designs in statistics, we often need to maximize a homogeneous polynomial as a function of proportions. We introduce two analytic approaches to solve D-optimal approximate designs under generalized linear models. The first approach provides analytic D-optimal allocations for generalized linear models with two factors. The second approach leads to explicit solutions for a class of generalized linear models with more than two factors. There are many other similar optimization problems of homogenous polynomials that are open and have potential applications in statistics.