Models and Designs for Mixture Experiments

Linda Haines,an Emeritus Professor in the Department of Statistical Sciences will present the Department of Statistical Sciences seminar with a talk entitled, "Models and Designs fo r Mixture Experiments".

Consider an experiment in which the proportions of charcoal, sulphur and saltpetre which yield the largest bang are to be determined. The problem, more formally, is to adopt a model for the response to the proportions and then to design an experiment in order to identify the requisite optimal proportions. In this talk, the background to mixture models and the attendant design problem is given and a new algorithm for the construction of optimal designs for an experiment with linear inequality constraints on the proportions is introduced.

Monday, September 5, 2016 - 13:00

Lecture Theatre 3, PD Hahn.