Fixed-design conditional power
Explore future rejection probability under a specified canonical normal drift.
Your entries stay in this page’s memory and are not submitted to us. Downloads are generated locally. Reloading or leaving the page clears your entries. Do not enter patient information.
Information fraction must lie strictly inside 0–1. Alpha is one-sided from 0.001 to 0.2. The final mean z is the assumed drift under a specific future effect, not the observed current z.
The starting values are hypothetical. Results update as you edit. Use aggregate or synthetic inputs only.
Calculation results
- Final rejection boundary
- 1.959964
- Conditional final mean z
- 2.2485281
- Conditional final SD
- 0.70710678
- Conditional power
- 0.65839669
How to interpret the output
Under independent Brownian increments, final z conditional on current z has mean sqrt(t)×zcurrent+(1−t)×drift and variance 1−t. The output is conditional probability of crossing a fixed upper final boundary. It ignores interim efficacy/futility stopping and adaptive changes; it must not be used to redesign a trial without appropriate statistical planning.
Method referenceSource checked 2026-11-06. Read the reproducible calculator validation report.