Expert knowledge is a valuable source of information to augment available data or when interpretation/synthesis of data requires expert judgement. Prior elicitation is a key tool for translating this expert knowledge and judgement into a quantitative probability distribution that can then be used in the design, analysis, and interpretation of clinical and observational studies. In this talk, we review the different approaches to elicit information from experts and summarize it in a probabilistic language, Bayesian prior distributions. We then focus on how expert knowledge from multiple experts can be summarized. Software to achieve such summaries is also discussed. The concepts and approaches are illustrated using a variety of real-life examples relating to different aspects of pharmaceutical product development. The talk shows Bayesian prior elicitation to be a feasible and useful aid to internal company decision making across the pharmaceutical product lifecycle chain.
VP and Head of Statistics and Data Science Innovation, GSK
In 2015, Nicky Best was awarded the RSS/PSI award for Statistical Excellence in the Pharmaceutical Industry for her role in implementing prior elicitation and statistical assurance to improve decision making in clinical drug development. In 2018 she received the Royal Statistical Society Bradford Hill Medal for her work on Bayesian methods in clinical trials, cost-effectiveness, epidemiology and drug development. She currently co-chairs the EFSPI/PSI Historical Data Special Interest Group. Before joining the pharmaceutical industry, Nicky was an academic statistician at the Medical Research Council Biostatistics Unit in Cambridge UK and at Imperial College London, where she was Professor of Statistics and Epidemiology. She served as editor-in-chief of the Journal of the Royal Statistical Society, Series A (Statistics in Society) from 2001 to 2004, as Director of one of the research nodes of the UK Economic and Social Research Council National Centre for Research Methods from 2005-2011, and as Biostatistics Theme Lead for the UK Medical Research Council Centre for Environment and Health.
Senior Advisor, Data Science, PharmaLex
Brad is a statistical researcher, methodologist, consultant, and instructor. Prior to joining PharmaLex, he spent 27 years on the faculty of the Division of Biostatistics at the University of Minnesota School of Public Health, serving as division head for 7 of those years. He has published more than 185 papers in refereed books and journals, and has co-authored three popular textbooks on Bayesian statistical methods and their applications in spatial statistics and adaptive clinical trials. During his spare time, Brad is a health musician and bandleader, providing keyboards and vocals in a variety of venues. He is excited and proud to be a part of the PharmaLex data science and statistics team.