Designs for generalized linear models under model uncertainty


Woods, D. C. (2005) Designs for generalized linear models under model uncertainty At International Conference on Design of Experiments. 13 - 15 May 2005.

Download

Full text not available from this repository.

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 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. Designs are investigated for practical applications and their advantages are discussed.

Item Type: Conference or Workshop Item (Other)
Venue - Dates: International Conference on Design of Experiments, 2005-05-13 - 2005-05-15
Subjects:
Organisations: Statistics
ePrint ID: 15868
Date :
Date Event
15 May 2005Published
Date Deposited: 06 Jun 2005
Last Modified: 16 Apr 2017 23:26
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/15868

Actions (login required)

View Item View Item