Optimum design for mixed effects non-linear and generalised linear models

Workshop theme

Mixed effects non-linear and generalized linear models have recently received a considerable interest with respect to modelling issues and statistical analysis. However, the theory of optimum design for such models has got somewhat less attention in the statistical literature. In 2006 a small meeting, Population Optimum Design of Experiments (PODE) started a series of annual workshops dedicated to the theory and applications of design of experiments for PK/PD mixed models, see http://www.maths.qmul.ac.uk/~bb/PODE/PODE. However, the theory of design for mixed-effects models has been developed independently of any applications as well as for other specific problems, for example choice experiments. Hence, we would like to get together a wider group of those interested in the area of design of experiments for mixed-effects generalized linear models and non-linear models, to share their experience and to further the theory.

Optimum design theory cannot develop without a good knowledge of statistical issues in modelling, estimation and hypothesis testing. Hence, we plan to have talks in these topics together with talks on experimental design. We plan to include PODE in the workshop and have talks in the area of optimum design for population PK/PD models. This will be the last day of the workshop, that is, Friday 12th of August.

We will have dedicated one-hour lectures, invited and contributed talks, poster sessions as well as a lot of time for informal discussions.

The application is closed

Timetable

Tuesday 9th August 2011
09:00 to 09:25	Registration	No Room Required
09:25 to 09:30	Opening remarks and welcome from John Toland (INI Director Designate)	No Room Required
09:30 to 10:30	Douglas Bates University of Wisconsin-Madison Lecture on modelling: Mixed effects non-linear and generalized linear models	Room 1
10:30 to 11:00	Morning coffee	No Room Required
11:00 to 11:45	Rainer Schwabe Otto-von-Guericke-Universität Magdeburg "To estimate or to predict" - implications on the design for linear mixed models	Room 1
11:45 to 12:30	Alexander Donev University of Manchester Experimental designs for estimating variance components	Room 1
12:30 to 13:30	Lunch at Wolfson Court	No Room Required
14:00 to 14:45	Steven Gilmour University of Southampton GLMs and GLMMs in the analysis of randomized experiments	Room 1
14:45 to 15:30	Block designs for non-normal data via conditional and marginal models	Room 1
15:30 to 16:00	Afternoon tea	No Room Required
16:00 to 16:45	Tim Waite University of Southampton Designs for mixed models with binary response	Room 1
16:45 to 17:30	Welcome wine reception	No Room Required

Wednesday 10th August 2011
09:30 to 10:30	Eugene Demidenko Dartmouth College Lecture on estimation and inference: Non-maximum likelihood estimation and statistical inference for linear and nonlinear mixed models	Room 1
10:30 to 11:00	Morning coffee	No Room Required
11:00 to 11:45	Sebastian Ueckert Uppsala Universitet Optimal design of clinical trials in Alzheimer's disease	Room 1
11:45 to 12:30	France Mentré Université Paris 7 - Denis-Diderot Optimal designs for pharmacokinetic and viral dynamic nonlinear mixed effect models in HIV treatment	Room 1
12:30 to 13:30	Lunch at Wolfson Court	No Room Required
14:00 to 14:45	Gary Rosner Johns Hopkins University Bayesian enrichment strategies for randomized discontinuation trials	Room 1
14:45 to 15:30	Peter Mueller University of Texas at Austin Sequential stopping for high-throughput experiments	Room 1
15:30 to 16:00	Afternoon tea	No Room Required
16:00 to 16:30	Douglas Bates University of Wisconsin-Madison Profiling the deviance to assess variability of parameter estimates in mixed models	Room 1
16:00 to 17:30	Poster storm and Posters	Discussion Room

Thursday 11th August 2011
09:30 to 10:30	Val Fedorov None / Other Mixed models: design of experiments	Room 1
10:30 to 11:00	Morning coffee	No Room Required
11:00 to 11:45	Krzysztof Patan University of Zielona Góra Group sensor scheduling for parameter estimation of random-effects distributed systems	Room 1
11:45 to 12:30	Mahbub Latif University of Dhaka Optimum designs for transform-both-sides nonlinear mixed effects model in the presence of covariates	Room 1
12:30 to 13:30	Lunch at Wolfson Court	No Room Required
14:00 to 17:30	Cambridge Colleges Tour	No Room Required
19:00 to 22:00	Conference dinner at Peterhouse	No Room Required

Friday 12th August 2011
09:30 to 09:45	Intro by B Bogacka and S Leonov	Room 1
09:45 to 10:30	Sergei Leonov Vertex Pharmaceuticals Approximation of the individual Fisher information matrix and its use in design of population PK/PD studies	Room 1
10:30 to 11:00	Morning coffee	No Room Required
11:00 to 11:45	Tobias Mielke Otto-von-Guericke-Universität Magdeburg Approximation of the Fisher information and design in nonlinear mixed effects models	Room 1
11:45 to 12:30	Joakim Nyberg Uppsala Universitet Improved conditional approximations of the population Fisher information matrix	Room 1
12:30 to 13:30	Lunch at Wolfson Court	No Room Required
14:00 to 14:45	Timothy Waterhouse Eli Lilly and Company Experiences in optimal design for population PK/PD models	Room 1
14:45 to 15:30	Steve Duffull University of Otago A general method to determine sampling windows for nonlinear mixed effects models	Room 1
15:30 to 16:00	Afternoon tea	No Room Required
16:00 to 16:30	France Mentré Université Paris 7 - Denis-Diderot Software for the population optimum design of experiments	Room 1
16:30 to 17:00	Discussion	Room 1

Optimum design for mixed effects non-linear and generalised linear models

Speakers

Douglas Bates University of Wisconsin-Madison
Eugene Demidenko Dartmouth College
Alexander Donev University of Manchester
Steve Duffull University of Otago
Val Fedorov None / Other
Steven Gilmour University of Southampton
Mahbub Latif University of Dhaka
Sergei Leonov Vertex Pharmaceuticals
France Mentré Université Paris 7 - Denis-Diderot
Tobias Mielke Otto-von-Guericke-Universität Magdeburg
Peter Mueller University of Texas at Austin
Joakim Nyberg Uppsala Universitet
Krzysztof Patan University of Zielona Góra
Gary Rosner Johns Hopkins University
Rainer Schwabe Otto-von-Guericke-Universität Magdeburg
Sebastian Ueckert Uppsala Universitet
Tim Waite University of Southampton
Timothy Waterhouse Eli Lilly and Company

Show All

Optimum design for mixed effects non-linear and generalised linear models

Workshop theme

The application is closed

Timetable

Speakers

Supported By

Register for updates