Drug Evaluation Committee Causal Inference for Understanding ICH E9(R1) - Time Dependent Treatment
Data Science Subcommittee
September 2022
The causal inference methods discussed in "Causal Inference for Understanding ICH E9(R1)" published in July 2022 were based on the idea of time-fixed treatment. In reality, however, there are many cases in which we are interested in causal contrasts, including time-varying treatment. We believe that understanding the concept of causal inference for time-varying treatment will be useful in defining treatment regimens that include time-varying treatment, and in establishing the associated estimand.
Therefore, we, the subteam of Task Force 4, Estimation of Time-Dependent Treatment by Causal Inference, Continuing Task Force 2022, Data Science Subcommittee, Drug Evaluation Committee, Japan Pharmaceutical Manufacturers Association (JPMA), have described in this deliverable the basic concept of causal inference for time-dependent treatment, each estimation method, application examples, and SAS implementation examples.
We hope that this publication will help you to understand ICH E9(R1) and to plan, analyze, and interpret the results of clinical trials and observational studies that are interested in treatment regimens, including time-dependent therapies.
Japan Pharmaceutical Manufacturers Association, Committee on Drug Evaluation
DS Subcommittee 2022 Ongoing Task Force 4
Deliverables of the Drug Evaluation Committee Return to list of all deliverables