Optimal designs for minimising covariances among parameter estimators in a linear model

Mandal, S., Torsney, B. and Chowdhury, M. (2017) Optimal designs for minimising covariances among parameter estimators in a linear model. Australian and New Zealand Journal of Statistics, 59(3), pp. 255-273. (doi: 10.1111/anzs.12195)

[img]
Preview
Text
149214.pdf - Accepted Version

563kB

Abstract

We construct approximate optimal designs for minimising absolute covariances between least-squares estimators of the parameters (or linear functions of the parameters) of a linear model, thereby rendering relevant parameter estimators approximately uncorrelated with each other. In particular, we consider first the case of the covariance between two linear combinations. We also consider the case of two such covariances. For this we first set up a compound optimisation problem which we transform to one of maximising two functions of the design weights simultaneously. The approaches are formulated for a general regression model and are explored through some examples including one practical problem arising in chemistry.

Item Type:Articles
Additional Information:The research of S. Mandal is supported by a Discovery Grant from the Natural Sciences and Engineering Research Council (NSERC) of Canada.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Torsney, Dr Bernard
Authors: Mandal, S., Torsney, B., and Chowdhury, M.
College/School:College of Science and Engineering > School of Mathematics and Statistics > Statistics
Journal Name:Australian and New Zealand Journal of Statistics
Publisher:Wiley
ISSN:1369-1473
ISSN (Online):1467-842X
Published Online:27 September 2017
Copyright Holders:Copyright © 2017 Australian Statistical Publishing Association Inc.
First Published:First published in Australian and New Zealand Journal of Statistics 59(3): 255-273
Publisher Policy:Reproduced in accordance with the publisher copyright policy

University Staff: Request a correction | Enlighten Editors: Update this record