A delimitation of the support of optimal designs for Kiefer's ϕpϕ_p-class of criteria

preprint2013arXivOpen access

Abstract

The paper extends the result of Harman and Pronzato [Stat. & Prob. Lett., 77:90--94, 2007], which corresponds to p=0p=0, to all strictly concave criteria in Kiefer's ϕpϕ_p-class. Let ξξ be any design on a compact set X⊂RmX\subset\mathbb{R}^m with a nonsingular information matrix $\Mb(ξ)$, and let δδ be the maximum of the directional derivative Fϕp(ξ,x)F_{ϕ_p}(ξ,x) over all x∈Xx\in X. We show that any support point x∗x_* of a ϕpϕ_p-optimal design satisfies the inequality $F_{ϕ_p}(ξ,x_*) \geq h_p[\Mb(ξ),δ]$, where the bound $h_p[\Mb(ξ),δ]$ is easily computed: it requires the determination of the unique root of a simple univariate equation (polynomial when pp is integer) in a given interval. The construction can be used to accelerate algorithms for ϕpϕ_p-optimal design and is illustrated on an example with AA-optimal design.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.