Is it suitable for academic or professional research?

Absolutely. The skill follows scientific best practices by calculating not just p-values, but also effect sizes and confidence intervals to provide a complete picture of statistical significance.

Which Python libraries are required for this skill?

The skill utilizes industry-standard libraries including Pandas for data manipulation, NumPy for numerical computations, and SciPy or Statsmodels for advanced statistical testing.

Does it provide visual data verification?

Yes, it includes patterns for visual assumption checking, such as generating and saving Q-Q plots to verify normality through Matplotlib integration.

Can this skill handle data that isn't normally distributed?

Yes, it includes robust non-parametric alternatives such as the Mann-Whitney U test, Cliff's Delta for effect size, and Permutation tests for complex data distributions.

How does the skill handle memory constraints during analysis?

It features dedicated memory management patterns, including tracking DataFrame size in MB and implementing explicit garbage collection for large-scale data processing.

Data Analysis & Statistical Patterns

Name: Data Analysis & Statistical Patterns
Author: Yeachan-Heo

byYeachan-Heo

•

120

データサイエンスとML

Implements rigorous data exploration, statistical testing, and scientific validation patterns using Python's data science stack.

概要

This skill provides a standardized framework for performing comprehensive data analysis within Claude Code, specifically tailored for scientific research and data-driven decision-making. It bridges the gap between raw data and actionable insight by offering robust patterns for exploratory data analysis (EDA), hypothesis testing, and critical assumption verification. Whether you are validating experimental results or profiling datasets for machine learning, this skill ensures statistical rigor through built-in support for effect sizes, multiple confidence interval methods, and non-parametric alternatives, while maintaining efficiency through proactive memory management.

主な機能

120 GitHub stars
Standardized patterns for automated Exploratory Data Analysis (EDA) and descriptive statistics
Rigorous statistical hypothesis testing including T-Tests, ANOVA, and Permutation tests
Comprehensive assumption checking for normality, homogeneity of variance, and independence
Automated effect size calculations (Cohen's d, r², Cliff's Delta) for substantive interpretation
Advanced confidence interval generation using parametric, bootstrap, and Wilson score methods

ユースケース

Validating experimental research data and results with scientific-grade statistical rigor
Conducting A/B test analysis to compare treatment groups with robust non-parametric alternatives
Cleaning and profiling large datasets to identify distributions and outliers before ML modeling

概要

主な機能

120 GitHub stars
Standardized patterns for automated Exploratory Data Analysis (EDA) and descriptive statistics
Rigorous statistical hypothesis testing including T-Tests, ANOVA, and Permutation tests
Comprehensive assumption checking for normality, homogeneity of variance, and independence
Automated effect size calculations (Cohen's d, r², Cliff's Delta) for substantive interpretation
Advanced confidence interval generation using parametric, bootstrap, and Wilson score methods

ユースケース

Validating experimental research data and results with scientific-grade statistical rigor
Conducting A/B test analysis to compare treatment groups with robust non-parametric alternatives
Cleaning and profiling large datasets to identify distributions and outliers before ML modeling