Introduction to causal inference and directed acyclic graphs

Registration for this event has closed

Estimating causal effects in non-experimental data is a key aim of applied health and social science research. Unfortunately, it is also notoriously difficult. Contemporary causal inference methods, including directed acyclic graphs, promise to revolutionise the analysis and interpretation of non-experimental data, not least by making our ambitions and assumptions far more explicit. This interactive session offers a friendly and non-technical introduction to the theory, practice, and benefits of contemporary causal inference methods and directed acyclic graphs. Particular focus will be given to considering how these methods can contribute towards more transparent and reproducible research.

Facilitated by Peter WG Tennant.

Learning objectives:

• Appreciate ‘description’, ‘prediction’ and ‘causal inference’ as three distinct scientific tasks requiring distinct scientific methods
• Understand the main features of causal directed acyclic graphs and how they can be used to plan and interpret causal analyses
• Appreciate some of the challenges and implications of using directed acyclic graphs in applied research

Timetable (GMT+1 / BST):

14:00-14:45 – Introduction to causal inference and directed acyclic graphs

14:45-14:55 – Questions

15:00-15:05 – Break

15:05-15:45 – Directed acyclic graphs in practice

15:45-16:00 – Questions