statistical-reviewer

Review clinical trial datasets for statistical accuracy and consistency.

93|23|Updated Mar 4, 2026

Search Tags:#data integrity #reproducibility #statistical review #clinical trial data #realism assessment

Ready to run

npx skills add https://github.com/RConsortium/pharma-skills --skill statistical-reviewer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: statistical-reviewer
Source: https://github.com/RConsortium/pharma-skills/tree/main/statistical-reviewer
Command: npx skills add https://github.com/RConsortium/pharma-skills --skill statistical-reviewer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, scipy, lifelines, statsmodels, pyreadstat, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simulates an independent statistical review of clinical trial data, ensuring accuracy, integrity, and consistency of reported results.

Core Features & Use Cases

Data Integrity Review: Identifies errors, inconsistencies, and missing data in clinical trial datasets (SDTM, ADaM, TLF, SAP, CSR).
Reproducibility Checks: Validates the reproducibility of statistical analyses and reported results.
Realism Assessment: Assesses whether the data exhibits the natural variation and operational patterns expected from real clinical trials.
Use Case: If you have a clinical trial dataset and want to ensure the accuracy of the reported results, use this Skill to conduct a comprehensive review.

Quick Start

Use the statistical-reviewer skill to review the provided clinical trial dataset and report any findings.

Frequently Asked Questions about statistical-reviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I conduct an independent statistical review of clinical trial datasets?▼

Conduct a statistical review by analyzing SDTM, ADaM, TLF, SAP, and CSR data layers to validate data integrity, reproducibility, and realism. This process identifies inconsistencies and ensures reported results accurately match the underlying clinical trial data.

What is realism assessment in clinical trial data?▼

Realism assessment evaluates whether clinical trial datasets exhibit the natural variation and operational patterns expected from real-world studies. It checks for authentic data behavior to ensure the statistical review validates genuine operational outcomes.

Can I use pandas and scipy to validate reproducibility of clinical trial analyses?▼

Yes, you can validate reproducibility using pandas, scipy, statsmodels, and lifelines to analyze SDTM and ADaM datasets. These dependencies support complex statistical methods to verify that reported results are consistent and reproducible.

Does this statistical review approach work with SDTM and ADaM data standards?▼

Yes, the statistical review process works directly with SDTM and ADaM data standards alongside TLF, SAP, and CSR documents. It requires these specific clinical trial data layers to identify errors and verify the accuracy of reported outcomes.

How do I check clinical trial data integrity for missing values and inconsistencies?▼

Check data integrity by reviewing clinical trial datasets to identify errors, missing data, and inconsistencies across SDTM, ADaM, and TLF layers. The review applies complex statistical methods to ensure results align with the underlying data.

What are the limitations of using pyreadstat for statistical review of clinical data?▼

While pyreadstat enables reading SAS data files for statistical review, the process requires comprehensive analysis across multiple data layers including SAP and CSR documents. It focuses on clinical trial data integrity and reproducibility rather than standalone data parsing.