Can I optimize truncation parameters using this skill?

Yes, it includes simulation-based strategies for optimizing gamma values to find the best trade-off between conservative error spending and statistical power.

Which multiplicity procedures are supported by this skill?

The skill supports a wide array of procedures including Bonferroni, Holm, Hochberg, Hommel, Fixed-Sequence, Fallback, and complex Graphical or Gatekeeping methods.

How does this skill handle endpoint hierarchies?

It provides specific implementation patterns for gatekeeping (parallel and multiple-sequence) to ensure secondary endpoints are only tested when primary endpoint criteria are met.

Does it provide code for FWER validation?

Absolutely. The skill includes best practices and R code snippets for validating Family-Wise Error Rate control under the global null hypothesis to ensure regulatory compliance.

Clinical Trial Multiplicity Methods

Name: Clinical Trial Multiplicity Methods
Author: choxos

bychoxos

0•

データサイエンスとML

Implements and optimizes multiplicity adjustment procedures to control Family-Wise Error Rate (FWER) in clinical trial simulations.

This skill provides a comprehensive reference and implementation guide for advanced statistical testing procedures within clinical trial designs. It assists biostatisticians and developers in selecting and coding appropriate multiplicity adjustments—ranging from simple Bonferroni and Holm procedures to complex graphical testing and gatekeeping strategies. By providing structured R code patterns and optimization logic for truncation parameters, this skill ensures rigorous Type I error control and maximized statistical power across multi-arm and multi-endpoint trials.

主な機能

01Implementation patterns for single-step, step-down, and step-up procedures (Holm, Hochberg, Hommel)

02Optimization strategies for truncation parameters (gamma) to balance power and error spending

03Graphical testing procedures with flexible weight transfers and hypothesis recycling

040 GitHub stars

05Advanced gatekeeping frameworks including parallel, multiple-sequence, and mixture structures

06Standardized FWER validation protocols under global null hypothesis conditions

ユースケース

01Designing multiplicity adjustment strategies for Phase III pivotal clinical trials

02Optimizing statistical power in multi-dose trials using simulation-based gamma tuning

03Implementing hierarchical testing logic for primary, secondary, and exploratory endpoints

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add choxos/biostatagent multiplicity-methods

For use in Claude.ai and ChatGPT

主な機能

01Implementation patterns for single-step, step-down, and step-up procedures (Holm, Hochberg, Hommel)

02Optimization strategies for truncation parameters (gamma) to balance power and error spending

03Graphical testing procedures with flexible weight transfers and hypothesis recycling

040 GitHub stars

05Advanced gatekeeping frameworks including parallel, multiple-sequence, and mixture structures

06Standardized FWER validation protocols under global null hypothesis conditions

ユースケース

01Designing multiplicity adjustment strategies for Phase III pivotal clinical trials

02Optimizing statistical power in multi-dose trials using simulation-based gamma tuning

03Implementing hierarchical testing logic for primary, secondary, and exploratory endpoints