Prof Thomas Jaki from the Medical and Pharmaceutical Statistics Research Unit at Lancaster University provides an overview of the professional development courses offered at the unit
The Medical and Pharmaceutical Statistics Research Unit was established directorship of Professor John Whitehead at The University of Reading in 1994. In 2007, the unit relocated to Lancaster University, where it is part of the Department of Mathematics and Statistics. The unit exists to develop and evaluate novel statistical methods of study design and data analysis relevant to pharmaceutical companies and medical research institutes.
The unit undertakes methodological research, often in direct collaboration with companies and provides professional development courses and a consultancy service. Our main areas of research are: pharmacological modelling, dose-escalation studies, Bayesian decision procedures, adaptive clinical trials and survival analysis.
Professional development courses
Commissioned courses: All the professional development courses may be commissioned by a company or organisation, tailored to meet your special requirements and presented at a location of your choice. Please contact us at email@example.com to discuss your specific requirements or for further information.
Scheduled courses: A selection of professional development courses are scheduled each year for presentation at Lancaster University, some of which also constitute part of our MSc in Statistics.
Scheduled courses at Lancaster University
Data and Safety Monitoring Boards (half a day)
Data and Safety Monitoring Boards (DSMBs) are a common feature of long-term clinical studies in serious and life-threatening conditions. This workshop describes the remit and composition of DSMBs and how their work relates to other parties involved in the study, such as the sponsor, the study project team.
Consideration is given to the nature and purpose of safety and efficacy data reports presented to the DSMB and the balance between the timeliness and accuracy of the data available is discussed. Statistical problems inherent in repeatedly making multiple treatment comparisons are highlighted and formal stopping guidelines based on repeated safety analyses are presented.
Pharmacological Modelling (three days)
Pharmacological models are used to describe the pharmacokinetics (PK) and pharmacodynamics of drug administration. The former concerns how the drug becomes distributed within the body and the latter how drug concentrations are related to physiological effects. The way in which models are derived from simplified representations of the body and approaches to the estimation of model parameters will be described. More advanced hierarchical models and Bayesian methods for population pharmacokinetics will be discussed.
Practicals will provide an opportunity for participants to fit simple models to data and to design and evaluate phase I dose-escalation studies.
Survival and Event History Analysis (three days)
In many medical applications, interests lie in times to or between events. Examples include the time from diagnosis of cancer to death or times between epileptic seizures. This course begins with a review of the standard approaches to the analysis of censored survival data. Survival models and estimation procedures are reviewed, and the emphasis is placed on the underlying assumptions, how these might be evaluated through diagnostic methods and how robust the primary conclusions might be to their violation. The study design is considered, in particular how to define events and censoring and how to determine a suitable sample size and duration of follow-up. Each lecture is complemented by a practical session implementing the methods using R.
Adaptive Methods in Clinical Research (three days)
The development of a new treatment in therapeutic areas such as cardiovascular disease, cancer or stroke are complex undertakings. There is a great interest from the pharmaceutical industry in the possibility that clinical trials can be designed with adaptive features that have the potential to save development costs and to shorten the time-to-market of a new treatment. These adaptive features include selecting the most promising treatments among several alternative ones, stopping a trial early for either efficacy and/or futility and sample size changes.
This course will introduce different adaptive methods and critically evaluate them. Practical sessions and discussion groups are looking at the implementation of these methods to supplement traditional lectures.
Designing Phase I Dose-Escalation Trials (two days)
The importance of exploratory clinical research prior to the launch of a large-scale definitive phase III clinical trial is becoming increasingly recognised. Dose-escalation studies are the first-in-human studies which aim to determine a safe dose or range of doses which can be taken forward for further development. Advances in the identification of medical biomarkers of therapeutic effect and in statistical techniques, based on adaptive designs and Bayesian inference, now allow such studies to be designed efficiently, to consider the information from a variety of sources and to combine various objectives, such as establishing safety and seeking evidence of a potential benefit.
This course presents a state-of-the-art methodology for dose-escalation studies. The course will be delivered through a mixture of lectures, practical sessions and discussion sessions.
Other courses available for commission
- Sample Size Determination in Clinical Trials (one to two days);
- Bayesian Methods for Clinical Trials (one to three days);
- Designing Early Phase Clinical Trials (one to three days) and;
- Adaptive methods for non-statisticians (one day).
Please note: this is a commercial profile
Prof Thomas Jaki
Professor of Statistics
Medical and Pharmaceutical Statistics
Tel: +44 (0)1524 59 23 18