pymc-labs/CausalPy

Health v2 · maintenance only

Adoption not part of the score

1185 stars · 114 forks observed · 2026-09-01

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

CausalPy is a Python package for causal inference in quasi-experimental settings, offering methods like difference-in-differences, synthetic control, regression discontinuity, and interrupted time series. It provides Bayesian estimation via PyMC with full uncertainty quantification, plus OLS via scikit-learn, with decision-ready effect summaries and plots.

Use cases

• estimate causal effects of an intervention without a randomized experiment
• run a difference-in-differences analysis in Python
• build a synthetic control model to measure a policy impact
• analyze interrupted time series around a product launch
• perform regression discontinuity analysis
• get Bayesian credible intervals for treatment effects
• measure lift from a marketing campaign or A/B-like test

When to choose

• you need quasi-experimental causal inference methods in Python
• you want Bayesian uncertainty quantification for causal effect estimates
• you want publication-quality plots and effect summaries with HDI and ROPE

When to avoid

• you need fully randomized A/B experiment analysis tooling
• you need a non-Python or GUI-based statistics environment
• you only need simple descriptive statistics or dashboards

Facets

library · maturity active

data-science machine-learning math data-science analytics machine-learning python causal-inference quasi-experiments bayesian pymc difference-in-differences synthetic-control statistics

Member repositories

For agents

markdown · JSON · MCP: product_card(name="pymc-labs/CausalPy")