This repository contains the materials for the Causal Survival Analysis workshop developed by Eleanor Murray, Ellen Caniglia, and Lucia Petito.
This workshop has been presented at conferences and universities around the world and has been published in Research Methods in Medicine & Health Sciences Journal, "Causal Survival Analysis: A guide to estimating intention-to-treat and per-protocol effects from randomized clinical trials with non-adherence and loss to follow-up" (2020) here.
This workshop is designed to provide an overview to causal inference for survival outcomes with point exposures or static time-varying exposures, where interventions are known at baseline, are of interest using inverse probability weighted discrete hazards models. A static intervention is one where the exposure should take the same value at every time point (e.g. continuous treatment versus never treatment).
The data for the workshop are a simulated version of the Coronary Drug Project trial. The workshop is available for SAS, R, and Stata users. Please ensure that you have downloaded the correct version of the dataset for your preferred coding language. The workshop instructions are provided as a single file regardless of programming language. A solutions manual is also available.
Please direct any comments, errors, or suggestions to Dr Ellie Murray at ejmurray@bu.edu.