Skip to main navigation Skip to search Skip to main content

KL-optimum designs: theoretical properties and practical computation

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper some new properties and computational tools for finding KL-optimum designs are provided. KL-optimality is a general criterion useful to select the best experimental conditions to discriminate between statistical models. A KL-optimum design is obtained from a minimax optimization problem, which is defined on a infinite-dimensional space. In particular, continuity of the KL-optimality criterion is proved under mild conditions; as a consequence, the first-order algorithm converges to the set of KL-optimum designs for a large class of models. It is also shown that KL-optimum designs are invariant to any scale-position transformation. Some examples are given and discussed, together with some practical implications for numerical computation purposes.

Original languageEnglish
Pages (from-to)107-117
Number of pages11
JournalStatistics and Computing
Volume26
Issue number1-2
DOIs
Publication statusPublished - 1 Jan 2016

Keywords

  • Continuity
  • Convexity
  • Discrimination
  • Generalized linear models
  • Infinite-dimensional spaces
  • Invariance
  • KL-optimality
  • Optimum design
  • Regular designs
  • Weak convergence metric

Fingerprint

Dive into the research topics of 'KL-optimum designs: theoretical properties and practical computation'. Together they form a unique fingerprint.

Cite this