Optimal design of experiments for implicit models

Belmiro P.M. Duarte, Anthony C. Atkinson, Jose F.O Granjo and Nuno M.C Oliveira

LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library

Abstract: Explicit models representing the response variables as functions of the control variables are standard in virtually all scientific fields. For these models, there is a vast literature on the optimal design of experiments (ODoE) to provide good estimates of the parameters with the use of minimal resources. Contrarily, the ODoE for implicit models is more complex and has not been systematically addressed. Nevertheless, there are practical examples where the models relating the response variables, the parameters and the factors are implicit or hardly convertible into an explicit form. We propose a general formulation for developing the theory of the ODoE for implicit algebraic models to specifically find continuous local designs. The treatment relies on converting the ODoE problem into an optimization problem of the nonlinear programming (NLP) class which includes the construction of the parameter sensitivities and the Cholesky decomposition of the Fisher information matrix. The NLP problem generated has multiple local optima, and we use global solvers, combined with an equivalence theorem from the theory of ODoE, to ensure the global optimality of our continuous optimal designs. We consider D- and A-optimality criteria and apply the approach to five examples of practical interest in chemistry and thermodynamics. Supplementary materials for this article are available online.

Keywords: model-based optimal designs; continuous designs; implicit models; nonlinear programming (search for similar items in EconPapers)
JEL-codes: C1 (search for similar items in EconPapers)
Pages: 14 pages
Date: 2022-09-01
New Economics Papers: this item is included in nep-his
References: View references in EconPapers View complete reference list from CitEc
Citations:

Published in Journal of the American Statistical Association, 1, September, 2022, 117(539), pp. 1424 - 1437. ISSN: 0162-1459

Downloads: (external link)
http://eprints.lse.ac.uk/107584/ Open access version. (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ehl:lserod:107584

Access Statistics for this paper

More papers in LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library LSE Library Portugal Street London, WC2A 2HD, U.K.. Contact information at EDIRC.
Bibliographic data for series maintained by LSERO Manager (lseresearchonline@lse.ac.uk).