Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Statsmodels Statistical Modeling

Guides Claude through rigorous statsmodels work — OLS, GLM, discrete choice, and time series — with full diagnostics and inference.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Teaches Claude to use statsmodels, Python's flagship statistical modeling library, the right way: model selection → estimation → assumption testing → diagnostics → publication-ready reporting.

  • Regression: OLS, WLS, GLS, quantile regression, mixed effects
  • GLM: Binomial, Poisson, Gamma families and link-function choice
  • Discrete outcomes: Logit/Probit, multinomial, negative binomial, ZIP/ZINB, hurdle
  • Time series: stationarity tests (ADF/KPSS), ARIMA/SARIMAX/VAR, forecast intervals
  • Diagnostics: heteroskedasticity, autocorrelation, VIF, Cook's distance, robust/cluster SEs

Topic-specific references/ files keep detail out of the way until it's needed, and a 15-item pitfall list catches the classic mistakes.

Who it's for

  • Researchers and grad students who need coefficient tables and confidence intervals for publication
  • Econometricians and policy analysts where interpretation matters more than prediction
  • Data analysts comfortable with scikit-learn but rusty on standard errors and p-values
  • Forecasters who don't want to skip stationarity and residual checks

Example uses

  1. Sales regression: "Fit OLS of revenue on ad spend and season dummies, test for heteroskedasticity, and re-report with robust SEs" — includes residual plots, VIF, and influence checks.
  2. Churn interpretation: "Run a logistic regression on churn and give me odds ratios plus marginal effects" — flags convergence warnings and offers a Probit comparison.
  3. Monthly demand forecast: "Check stationarity with ADF/KPSS, then fit SARIMAX and forecast 12 months with intervals" — order identification from ACF/PACF plus a Ljung-Box residual test.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/statsmodels folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/statsmodels/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/statsmodels ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, WSL or Git Bash on Windows).
  2. Confirm Python 3.9+ is available: python3 --version
  3. Install the library: uv pip install statsmodels==0.14.6 (or pip install statsmodels==0.14.6). Add pip install scikit-learn if you want the predictive-metric examples.
  4. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  5. Create the skills folder: mkdir -p ~/.claude/skills
  6. Copy the skill in: cp -r scientific-agent-skills/skills/statsmodels ~/.claude/skills/
  7. Verify that ~/.claude/skills/statsmodels/references/ contains the reference markdown files.
  8. Restart Claude Code and try a prompt like "Fit an OLS model on this CSV and run full diagnostics."
View source on GitHub ↗License: MIT