Designs for generalized linear models with several variables and model uncertainty


Woods, D. C., Lewis, S. M., Eccleston, J. A. and Russell, K. G. (2006) Designs for generalized linear models with several variables and model uncertainty. Technometrics, 48, (2), 284-292. (doi:10.1198/004017005000000571).

Download

[img] PDF - Publishers print
Restricted to Registered users only

Download (313Kb) | Request a copy
[img] PDF - Post print
Download (191Kb)

Description/Abstract

Standard factorial designs may sometimes be inadequate for
experiments that aim to estimate a generalized linear model, for
example, for describing a binary response in terms of several
variables. A method is proposed for finding exact designs for such
experiments which uses a criterion that allows for uncertainty in
the link function, the linear predictor or the model parameters,
together with a design search. Designs are assessed and compared
by simulation of the distribution of efficiencies relative to
locally optimal designs over a space of possible models. Exact
designs are investigated for two applications and their advantages
over factorial and central composite designs are demonstrated.

Item Type: Article
ISSNs: 1537-2723 (print)
Keywords: binary response, d-optimality, logistic regression, robust design, simulation
Subjects: Q Science > QA Mathematics
H Social Sciences > HA Statistics
Divisions: University Structure - Pre August 2011 > School of Mathematics
University Structure - Pre August 2011 > Southampton Statistical Sciences Research Institute
University Structure - Pre August 2011 > School of Mathematics > Statistics
ePrint ID: 15828
Date Deposited: 14 Jun 2005
Last Modified: 14 Apr 2014 09:09
Contact Email Address: D.C.Woods@maths.soton.ac.uk
URI: http://eprints.soton.ac.uk/id/eprint/15828

Actions (login required)

View Item View Item