Overview
The NCI-sponsored short course 'Cluster Randomized Trial Designs in Cancer Care Delivery Research' is being held virtually on May 3, 4 and 5, 2022 from 11 am to 5 pm EST.
This short course will provide training in the design, conduct, and analysis of cluster randomized trials (CRTs), including parallel CRTs, stepped-wedge CRTs, and cluster randomized cross-over trials (CRXO). These trials are increasingly used to evaluate interventions to improve care delivery and to study strategies for implementing evidence-based interventions into routine clinical practice. They require specific methods of design and statistical analysis.
The course will address the rationale for using these designs, specific design issues, the randomization process, sample size calculations, analytical methods, ethical considerations, practical issues in managing these trials, and trial reporting and interpretation. Principles will be illustrated using case studies of the different variations of cluster randomized trials across the cancer control continuum (prevention, diagnosis, treatment, survivorship, and at end-of-life). Registration is free of charge.
This course has been designed to address the training needs of doctorally prepared cancer care delivery/implementation researchers (including statisticians and methodologists), as well as post-doctoral fellows and other trainees and other scientific team members such as project coordinators. Participants should have fundamental understanding of basic statistics, sources of bias in research designs, and the design, conduct and interpretation of individual-level randomized interventional trials in behavioural science/healthcare delivery. Some of the sessions are specifically targeted at statisticians, methodologists, and researchers with an interest in more complex statistical topics.
Objectives
By the end of this course, attendees will be able to critically appraise and apply a range of appropriate design approaches and analytical methods for cluster randomized trials (CRTs), including parallel CRTs, stepped-wedge CRTs, and cluster randomized cross-over trials (CRXO).
The course will cover:
- Key concepts of cluster randomized trials (also known as group-randomized trials), including the rationale for cluster randomization and measures of between-cluster variation
- Design of cluster randomized trials, including cluster selection and randomization procedures and different design variations such as the parallel CRT, the stepped-wedge CRT, and the cluster randomized cross-over design (CRXO)
- Risk of bias and justification for choosing a CRT design
- Power calculations and justification of sample size
- Analysis using both cluster-level summaries and individual-level data (random effects models and generalized estimating equations)
- Ethical considerations, data monitoring and study reporting and results dissemination
- Stakeholder perspectives on practical considerations and challenges when conducting CRTs, incorporating the diverse viewpoints of researchers, project managers, healthcare system leaders, community oncology research networks, reporting guideline developers, and journal editors