Educational articles about Simon's two-stage design, power functions, phase II trial design selection, sample size, early stopping, and BioStatHub workflows.
The Simon two-stage design calculator generates and compares the designs these articles explain. About BioStatHub describes who develops it and how it is validated.
20 min read | Beginner
Explains how Simon's two-stage design works in single-arm Phase II trials: the parameters and decision rules, Type I error and power, probability of early termination, expected sample size, a worked example, and how optimal, minimax, and admissible designs compare.
18 min read | Intermediate
A complete numerical walkthrough of one Phase II scenario: the statistical parameters, the two-stage decision rule, four candidate designs, the PET, expected sample size, Type I error and power calculations, and how to choose and document a design.
8 min read | Beginner
A practical guide to selecting p₀ and p₁ for Simon's two-stage designs, including the effect size concept, the four-way trade-off with α and β, and an iterative workflow for finding a feasible design.
5 min read | Beginner
A practical guide to choosing α and β in a Simon's two-stage design, including their clinical interpretation, effect on sample size, common choices, and how to justify them in a Phase II protocol.
9 min read | Beginner
Explains why Phase II trials use prospective futility rules, how Simon’s two-stage design balances patient protection with statistical power, and how PET and ESS make the benefit visible.
14 min read | Beginner
Explains how single-arm Phase II trials evaluate activity against a predefined benchmark, why historical comparability matters, and how two-stage designs support efficient development decisions.
9 min read | Intermediate
A practical guide to choosing between Simon's Optimal and Minimax two-stage designs by comparing expected sample size under p₀, early stopping, maximum enrollment, and the rationale behind each optimization objective.
8 min read | Intermediate
Explains how admissible designs form the Pareto frontier between Simon's optimal and minimax designs, and when a compromise design may be preferable.
10 min read | Intermediate
Learn how to choose among Optimal, Minimax, and admissible Simon's two-stage designs by comparing expected sample size, maximum sample size, early stopping, and operational priorities.
8 min read | Intermediate
Explains probability of early termination (PET), how it is calculated, why it depends on the true response rate, and how it balances with expected sample size, power, and type I error in Simon's two-stage designs.
14 min read | Advanced
Explains how adaptive Simon's two-stage designs let the second-stage sample size depend on the first-stage response count, why that makes the design search harder, and when the added complexity is worth it.
11 min read | Advanced
A numerical walkthrough of one Phase II scenario: the full response-dependent decision rule of an adaptive design, its operating characteristics next to Simon Optimal, where the adaptive design helps and where it barely does, and how the result can be checked independently.
9 min read | Intermediate
Explains how expected sample size depends on the response probability, how it relates to probability of early termination, and how it can help compare Simon's two-stage designs.
11 min read | Beginner
How sample size is determined for a single-arm Phase II trial, how Simon's two-stage designs calculate it, a worked example, and how to compare maximum and expected sample size.
14 min read | Beginner
A step-by-step guide to the BioStatHub workspace, from entering the study assumptions to a documented, exportable design decision.
17 min read | Intermediate
Explains how probability of early termination, probability of reaching stage 2, expected sample size, and the power function describe a Simon's two-stage design as a system, why each is a function of the true response probability rather than a fixed number, and how to read a three-panel operating-characteristics plot.
10 min read | Intermediate
Explains how the power function incorporates Stage 1 futility stopping and the final response rule, and how power curves help investigators compare and select Simon's two-stage designs.