On the regularization of singular c-optimal designs

Abstract : We consider the design of c-optimal experiments for the estimation of a scalar function h(t) of the parameters t in a nonlinear regression model. A c-optimal design x* may be singular, and we derive conditions ensuring the asymptotic normality of the Least-Squares estimator of h(t) for a singular design over a finite space. As illustrated by an example, the singular designs for which asymptotic normality holds typically depend on the unknown true value of t, which makes singular c-optimal designs of no practical use in nonlinear situations. Some simple alternatives are then suggested for constructing nonsingular designs that approach a c-optimal design under some conditions.
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00416002
Contributor : Luc Pronzato <>
Submitted on : Friday, September 11, 2009 - 4:01:14 PM
Last modification on : Monday, November 5, 2018 - 3:52:02 PM
Document(s) archivé(s) le : Tuesday, June 15, 2010 - 11:33:48 PM

File

Pronzato_Math-Slovaca-2008-rev...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00416002, version 1

Collections

Citation

Luc Pronzato. On the regularization of singular c-optimal designs. Mathematica Slovaca, 2009, 59 (5), pp.611-626. ⟨hal-00416002⟩

Share

Metrics

Record views

305

Files downloads

86