data-stats-analysis
This skill brings rigorous statistical testing to your LLM workflow using standard Python libraries (scipy, statsmodels, numpy) that execute locally in your environment. Perform t-tests, ANOVA, correlation analysis, multiple testing corrections, and non-parametric tests—all compatible with any LLM provider including GPT, Claude, Gemini, and others.
Statistical Analysis (Universal) performs hypothesis testing, t-tests, ANOVA, and correlation analysis using Python libraries that work with any LLM provider.
AI-generated summary based on this skill's SKILL.md
Install
beita6969/ScienceClaw/data-stats-analysis · repository language: TypeScript
git clone https://github.com/beita6969/ScienceClaw
cp -r ScienceClaw/skills/data-stats-analysis ~/.claude/skills/data-stats-analysisFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What statistical analysis python scipy capabilities does data-stats-analysis provide?
data-stats-analysis enables rigorous statistical hypothesis testing and significance analysis using standard Python libraries (scipy, statsmodels, numpy) that run locally in your environment. You can perform t-tests, ANOVA, correlation analysis, non-parametric tests like Mann-Whitney and Kruskal-Wallis, chi-square tests, and normality testing with Shapiro-Wilk—all without cloud dependencies.
How does data-stats-analysis handle multiple testing correction?
data-stats-analysis applies multiple testing corrections to control false discovery rate (FDR), including Bonferroni and other established methods. These corrections adjust p-values when conducting multiple comparisons, helping you avoid false positives and maintain statistical rigor across batch testing scenarios like differential gene expression analysis or cluster enrichment studies.
Can data-stats-analysis compare means across groups?
Yes, data-stats-analysis compares means across groups using t-tests for two-group comparisons, ANOVA for multiple groups, and non-parametric alternatives like Mann-Whitney and Kruskal-Wallis tests when data violates normality assumptions. It also supports post-hoc pairwise comparisons following ANOVA to identify which specific groups differ significantly.
What correlation and relationship analysis does data-stats-analysis support?
data-stats-analysis analyzes correlations and relationships between variables using both Pearson correlation (for linear relationships) and Spearman correlation (for monotonic relationships). These analyses help you detect associations in your data while providing p-values and confidence intervals to assess statistical significance.
Does data-stats-analysis work with any LLM provider?
Yes, data-stats-analysis is compatible with any LLM provider including GPT, Claude, Gemini, and others. It executes statistical tests locally using standard Python libraries, so you maintain full control over your analysis environment without vendor lock-in or cloud dependencies.
Can data-stats-analysis calculate effect sizes and confidence intervals?
data-stats-analysis calculates effect sizes (including Cohen's d) and confidence intervals for statistical results, giving you not just p-values but also practical measures of result magnitude. These metrics help you interpret whether statistically significant findings are also practically meaningful.
SKILL.md
rendered from the published skill — quoted content, verbatim
Statistical Analysis (Universal)
Overview
This skill enables you to perform rigorous statistical analyses including t-tests, ANOVA, correlation analysis, hypothesis testing, and multiple testing corrections. Unlike cloud-hosted solutions, this skill uses standard Python statistical libraries (scipy, statsmodels, numpy) and executes locally in your environment, making it compatible with ALL LLM providers including GPT, Gemini, Claude, DeepSeek, and Qwen.
When to Use This Skill
- Compare means between groups (t-tests, ANOVA)
- Test for correlations between variables
- Perform hypothesis testing with p-value calculation
- Apply multiple testing corrections (FDR, Bonferroni)
- Calculate statistical summaries and confidence intervals
- Test for normality and distribution fitting
- Perform non-parametric tests (Mann-Whitney, Kruskal-Wallis)
How to Use
Step 1: Import Required
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/data-stats-analysis/SKILL.md