Regression and Causal Modelling in Epidemiology

This course is an intermediate/advanced level course in the use of regression for effect estimation and causal modelling in epidemiology. The morning session will cover the basic principles of multiple regression analysis including assessment of confounding and multicollinearity, advanced methods for controlling multiple confounders, and the principles of assessment of effect measure modification. The afternoon session will cover more advanced topics including Directed Acyclic Graphs (DAGs), advanced methods for causal inference, and Bayesian methods. This session will also include an opportunity to discuss particular modelling issues arising from the research of the course participants.  This is not an introductory course, and participants will be required to have completed an introductory course in epidemiology and/or biostatistics or have equivalent research experience.

Presented by:  Professor Neil Pearce and Professor Debbie Lawlor

Professor Pearce is Professor of Epidemiology and Biostatistics, and Director of the Centre for Global NCDs, at the London School of Hygiene and Tropical Medicine. During 2000-2010 he was Director of the Centre for Public Health Research in the Research School of Public Health on the Massey University Wellington Campus. Since the completion of his PhD in epidemiology in 1985 he has been engaged in a wide range of public health research activities. During 1980-1988 his main research interest was in occupational epidemiology, and during this time he co-authored the leading textbook of occupational epidemiology, published by Oxford University Press in 1989 (the 2nd edition was published in 2004). In the 1990s he conducted a wide range of asthma research projects including the identification of the role of the asthma drug fenoterol in the New Zealand asthma mortality epidemic, studies of occupational asthma, studies of the management of asthma in the community, and more recently studies of the causes of the increases in asthma prevalence in New Zealand and worldwide. He has authored a textbook of asthma epidemiology which was published by Oxford University Press in 1998. He continues to work in a broad range of areas of epidemiological NCD research including epidemiological methods, respiratory disease, neurological disease, cancer, diabetes, indigenous health, and occupational and environmental health research. In 2008 he was made a Fellow of the Royal Society of New Zealand, and he was President of the International Epidemiological Association during 2008-2011.

Debbie Lawlor is Professor of Epidemiology at the School of Social and Community Medicine, University of Bristol. Professor Lawlor’s research is underpinned by an interest in understanding how biological, social and environmental exposures from across life affect the risk of chronic diseases and how, therefore, appropriate prevention of these diseases can be achieved. She has contributed to understanding the lifecourse and genetic epidemiology of obesity, diabetes, cardiovascular disease and women’s reproductive health; with a particular interest in the relationship between women’s reproductive health and her, and that of her offspring’s, cardiovascular risk. She is interested in developing methods for improving causal inference in epidemiology and has been at the forefront of developing and applying methods for using genetic variants as instrumental variables, non-genetic instrumental variables, cross-population studies and negative control studies for making causal inference.