The role of causal inference in biomedical research: dare we speak of ‘effect’? 4-Day Online Symposium

The field of causal inference has seen a massive expansion in recent years and is now one of the most active areas of biostatistical research. The concepts and tools developed in causal inference are intended to support practitioners in their quest for evidence on causal relationships, often critical for scientific progress. While powerful, these tools can also be easily misunderstood or misused — this has made some biostatisticians and epidemiologists apprehensive of the growing prominence of the field.

The symposium will address:

1. How causal inference can be leveraged to inform the design and enhance the analysis of observational and randomized studies, including combinations of both
2. How causal inference has stimulated the integration of machine learning into statistical inference
3. How causal inference provides clarity on assumptions that suffice to infer causality from different study designs and informs strategies for sensitivity analyses.

Details

• Dates: Saturday, November 22 – Tuesday, November 25, 2025
• Format: Online
• Time: 8:30 a.m. to 1 p.m. PST each day
• Short courses: Select full- and half-day online short courses will be offered Saturday November 15 and Sunday November 16, 2025. See short course tab for course titles.
• Register today to attend the Symposium and/or short courses!

Keynote Presentations

• Appropriate implementation of the estimands framework in clinical trials
  • Gregory Levin, PhD, Associate Director for Statistical Science and Policy, Office of Biostatistics, Food and Drug Administration.
• Evidence triangulation in dementia research
  • Maria Glymour, SD, Chair and Professor, Department of Epidemiology, Boston University.
• Unlocking the potential of EHR data for real-world evidence: opportunities and challenges
  • Tianxi Cai, ScD, Professor of Biomedical Informatics, Harvard Medical School; John Rock Professor of Population and Translational Data Sciences, Harvard T.H. Chan School of Public Health.
• Revisiting identification in the binary instrumental variable model: introducing the NATE
  • Eric Tchetgen Tchetgen, PhD, Professor of Biostatistics, Biostatistics and Epidemiology; Professor of Statistics and Data Science; The Wharton School, University of Pennsylvania.

More Information:

• Program Schedule
• Register Today!