Graphical Framework for Testing Hierarchically Structured Hypothesis Families

A novel graphical framework for managing hierarchically structured multiple testing in clinical trials, proposed by Zhiying Qiu. The method, represented as directed, weighted graphs, strongly controls the familywise error rate and is described in Markdown and R files totaling 16.4 KB. The framework was last updated on April 22, 2026.

Use Cases

• Designing family-based gatekeeping procedures based on the described graphical framework.
• Visualizing logical dependencies among hypothesis families using directed, weighted graphs.
• Comparing the performance of this method to serial, parallel, or tree-structured approaches via simulation.
• Applying the framework to a real clinical trial to manage multiple testing.

Strengths

• The method is formally proven to strongly control the familywise error rate.
• Simulation studies indicate performance comparable to hypothesis-level graphical approaches.
• Includes case studies and a real clinical trial application demonstrating practical use.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (16.4 KB), indicating it likely contains methodological code and documentation rather than extensive data.

Provenance

Source

figshare

Collection Method

Proposed methodological framework, likely accompanied by simulation code.

Time Range

null

Freshness

Last updated 2026-04-22 13:47:02; freshness should be verified.

Geography

null