Causal Inference in Epidemiology: Concepts and Methods
This course aims to define causation in biomedical research, describe methods to make causal inferences in epidemiology and health services research, and demonstrate the practical application of these methods.
|Date||4 - 7 July 2023|
|Structure||Taught over 4 consecutive full days|
|Audience||Open to all applicants|
|Course Organisers||Dr Amy Taylor, Dr Tom Palmer, Dr Raquel Granell, Professor Jonathan Sterne & Professor Kate Tilling|
Full course details
This 4-day course will run online and will consist of a mixture of lectures, small group work and computing practicals. Participants are encouraged to do the computing practicals on their own computer in breakout rooms with the help of a tutor. All sessions will be live.
By the end of the course participants should be able to:
- have a thorough understanding of the potential (counterfactual) outcomes approach to defining causal effects;
- implement Directed Acyclic Graphs (DAGs) to document assumptions and inform analysis plans;
- understand the key sources of bias in analyses of observational data, and how to investigate them using DAGs; and
- appreciate key methods which can be used to estimate causal effects, and understand the assumptions underlying them.
Who the course is intended for
This course is aimed at epidemiologists, statisticians and other quantitative researchers. Applicants must have knowledge and experience of a variety of linear and logistic regression models and their implementation in Stata, to beyond the level achieved in the Introduction to Linear and Logistic Regression Models course. Familiarity with survival analysis is recommended. We recommend that you do not attend this course in the same year that you have attended Introduction to Linear and Logistic Regression Models.
- potential (counterfactual) outcomes;
- causal diagrams (DAGs);
- confounding and methods to control for confounding (stratification, regression, propensity scores and inverse probability weighting);
- selection and information biases;
- model selection;
- instrumental variable estimation, including analysis of Mendelian randomization studies;
- time-varying confounding, marginal structural models and other g-methods;
- intention-to-treat and per-protocol effects in randomized trials;
- emulating a randomized trial using observational data;
- study designs for causal inference; and
IMPORTANT PREREQUISITES - please read before booking
Please ensure you meet the following prerequisites before booking:
|Knowledge||Applicants must have knowledge and experience of a variety of linear and logistic regression models and their implementation in Stata, to beyond the level achieved in the Introduction to Linear and Logistic Regression Models course. Familiarity with survival analysis is recommended.|
|Software||You must have Stata* (version 14, 15 or 16) installed in advance of the course.
*Internal University of Bristol participants are given access to Stata. Go to Stata Installation Instructions (internal only) for help setting it up before the start of the course. External participants are responsible for providing their own access to Stata.
This course is now fully booked
Join the waiting list via our online booking system.
Dates don't work? Just need a refresher?
Find out about the self-paced 'Materials Only' version of this course [available to University of Bristol staff and research postgraduates only].