Robust designs for binary data: applications of simulated annealing
Robust designs for binary data: applications of simulated annealing
When the aim of an experiment is the estimation of a generalized linear model (GLM), standard designs from linear model theory may prove inadequate. This paper describes a flexible approach for finding designs for experiments to estimate GLMs through the use of D-optimality and a simulated annealing algorithm. A variety of uncertainties in the model can be incorporated into the design search, including the form of the linear predictor, through use of a robust design-selection criterion and a postulated model space. New methods appropriate for screening experiments and the incorporation of correlations between possible model parameters are described using examples. An updating formula for D-optimality under a GLM is presented, which improves the computational efficiency of the search.
generalized linear models, optimal design, prior information, screening experiments, simulation
29-41
Woods, D.C.
ae21f7e2-29d9-4f55-98a2-639c5e44c79c
January 2010
Woods, D.C.
ae21f7e2-29d9-4f55-98a2-639c5e44c79c
Woods, D.C.
(2010)
Robust designs for binary data: applications of simulated annealing.
Journal of Statistical Computation and Simulation, 80 (1), .
Abstract
When the aim of an experiment is the estimation of a generalized linear model (GLM), standard designs from linear model theory may prove inadequate. This paper describes a flexible approach for finding designs for experiments to estimate GLMs through the use of D-optimality and a simulated annealing algorithm. A variety of uncertainties in the model can be incorporated into the design search, including the form of the linear predictor, through use of a robust design-selection criterion and a postulated model space. New methods appropriate for screening experiments and the incorporation of correlations between possible model parameters are described using examples. An updating formula for D-optimality under a GLM is presented, which improves the computational efficiency of the search.
Full text not available from this repository.
More information
Published date: January 2010
Keywords:
generalized linear models, optimal design, prior information, screening experiments, simulation
Identifiers
Local EPrints ID: 151261
URI: https://eprints.soton.ac.uk/id/eprint/151261
ISSN: 0094-9655
PURE UUID: f0fa240d-ac64-493d-9e9f-b9f57b7de88f
Catalogue record
Date deposited: 10 May 2010 09:52
Last modified: 02 Nov 2017 10:29
Export record
Contributors
University divisions
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics