Cookies

We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Department of Mathematical Sciences

Seminar Archives

On this page you can find information about seminars in this and previous academic years, where available on the database.

Statistics Seminars: Optimum mixture designs in a pharmaceutical experiment

Presented by Manisha Pal, University of Calcutta, India

27 July 2015 14:00 in CM221

Design of experiments has vast application in different fields, like engineering, agriculture, pharmaceutical, biomedical, environmental and epidemiological research. In some of these areas, especially in pharmaceutical research, the response is defined, not in terms of the actual amounts of different constituents used, but in terms of their relative proportions. Such a response function defines a mixture model.

Theoretically, the proportions of components in a mixture can vary between 0 and 1, subject to their sum being equal to 1. However, in practical situations, this is not realistic. For example, in preparing an inert matrix tablet there is a restriction on the proportions of the drug substances and the excipients in the tablet. There are also situations where the components of a mixture can be classified into a number of classes, depending on their type and function. There may be constraints on the proportions of these classes in the mixture. Such constraints are called relational constraints. In this presentation, I shall talk about optimum designs in mixtures with relational constraints in a pharmaceutical experiment.

Contact sunil.chhita@durham.ac.uk for more information