Conditional vs. unconditional bias in adaptive designs

A Conversation with Kaspar Rufibach

Why You Should Listen:

✔ You need clear, defensible language for papers, conferences, and labels when your study had interims and stopping rules.

✔ You’ll learn practical rules-of-thumb for when “naïve” estimates are okay—and when to adjust.

✔ You’ll hear what regulators typically focus on vs. what patients and clinicians actually want to know.

Episode Highlights:

02:00 – Why communicating adaptive results is hard (and how simple can still be correct)

04:14 – What bias are we actually interested in? Conditional vs. unconditional

07:20 – Consequences for point estimates and confidence intervals

09:15 – Ordering the sample space across stages; stage-wise ordering and p-values

12:23 – Median-unbiased estimation: what it is and when to use it

13:38 – Secondary endpoints, safety, and multiplicity strategies

16:13 – Estimation efficiency vs. unbiasedness: what should we optimize?

17:40 – Communicating to scientific vs. lay audiences

18:36 – Should we publish p-values for secondary endpoints in adaptive trials?

20:20 – No one-size-fits-all template—and why fairness matters across programs

20:30 – Pre-planning or bust: why post-hoc “fixes” don’t carry the properties we need

21:49 – Trust, reproducibility, and credible decision-making

23:16 – ICHE20: read it, comment, improve it

Links:

🔗 ICHE20 (Adaptive Clinical Trials) – draft guidance: worth reading for its perspective on estimation and communication.

🔗 The Effective Statistician Academy – I offer free and premium resources to help you become a more effective statistician.

🔗 Medical Data Leaders Community – Join my network of statisticians and data leaders to enhance your influencing skills.

🔗 My New Book: How to Be an Effective Statistician - Volume 1 – It’s packed with insights to help statisticians, data scientists, and quantitative professionals excel as leaders, collaborators, and change-makers in healthcare and medicine.

🔗 PSI (Statistical Community in Healthcare) – Access webinars, training, and networking opportunities.

Join the Conversation:
Did you find this episode helpful? Share it with your colleagues and let me know your thoughts! Connect with me on LinkedIn and be part of the discussion.

Subscribe & Stay Updated:
Never miss an episode! Subscribe to The Effective Statistician on your favorite podcast platform and continue growing your influence as a statistician.