Causal Inference in Addiction Research Pre-conference Workshop.
Tracks
.
| Sunday, November 12, 2023 |
| 9:00 AM - 1:00 PM |
| Riverbank 7 |
Details
Randomised controlled trials (RCTs) are the gold standard for causal inference. Randomisation removes all confounding and allows the treatment effect to be isolated. However, RCTs are conducted under tightly controlled environments and may have limited generalisability. They are also often not feasible in addiction research due to ethical or logistical reasons. Observational data from real-world settings are increasingly used to guide public health and clinical decisions. In this workshop, we will provide an overview of modern approaches to designing observational study that enable causal inferences. We will firstly cover three key techniques: Directed Acyclic Graphs (DAGs), modified Disjunctive Cause Criterion, Target Trial Emulation. We will then provide an overview on the counterfactual framework for causal inference and propensity score matching. We will illustrate these techniques using examples in addiction research and discuss the strength and limitations in their applications in addiction research.
Schedule
9.00-10.30 Introduction to Directed Acyclic Graphs (DAGs) and the Disjunctive Cause Criterion
10.30-10.50 Morning tea
10.50- 11.15 Introduction to Target Trial Emulation
11.15- 11.25 Q&A
11.25 – 1.00 Introduction to the counterfactual framework and Propensity Score Matching.
Speaker
A/Prof Gary Chan
Associate Professor
National Centre For Youth Substance Use Research
Designing observational studies for credible causal inference in addiction research – Directed Acyclic Graphs and modified Disjunctive Cause Criterion
Biography
A/Professor Gary Chan is a biostatistician and epidemiologist at the National Centre for Youth Substance Use Research, University of Queensland.
