igerber/diff-diff

Difference-in-Differences causal inference in Python. Callaway-Sant'Anna, Synthetic DiD, Honest DiD, event studies. sklearn-like API, validated against R.

What it solves

diff-diff is a comprehensive Python library for Difference-in-Differences (DiD) causal inference. It provides a standardized, sklearn-like API to implement a wide array of econometric methods used to measure the causal effect of an intervention (such as a marketing campaign, policy change, or product launch) by comparing treated and control groups over time.

How it works

The library implements numerous causal estimators that handle different data scenarios, including:

  • Staggered Adoption: Methods like Callaway & Sant'Anna and Sun & Abraham for when units are treated at different times.
  • Synthetic Control: Combining DiD with synthetic control methods for cases with very few treated units.
  • Complex Treatments: Support for reversible (non-absorbing) treatments, continuous treatments (dose-response), and triple-difference (DDD) designs.
  • Advanced Diagnostics: Tools for testing parallel trends, running placebo tests, and performing sensitivity analysis (e.g., Honest DiD) to check how results hold up under assumption violations.
  • Survey Integration: Built-in support for design-based variance estimation (strata, PSU, weights) for analyzing complex survey data like ACS or CPS.

Who it’s for

  • Econometricians and Data Scientists: Those performing rigorous causal analysis on panel or cross-sectional data.
  • Marketing Analysts: Professionals measuring campaign lift and product launch impact.
  • Policy Researchers: Analysts evaluating the effects of policy rollouts across different regions or time periods.

Highlights

  • Diverse Estimator Suite: Includes everything from basic 2x2 DiD and Two-Way Fixed Effects (TWFE) to cutting-edge methods like TROP and DMLDiD.
  • Rigorous Workflow: Provides a structured 8-step practitioner workflow (based on Baker et al. 2025) to ensure results are not just calculated but validated.
  • AI-Agent Ready: Includes a specialized get_llm_guide() function to provide LLMs with concise API references and workflows.
  • Comprehensive Diagnostics: Features tools for Bacon Decomposition, RD plots, and manipulation testing for Regression Discontinuity designs.

Related

  • Project
    laurencium/Causalinference

    A Python package for causal inference and treatment effect analysis using statistical and econometric methods.

  • Project
    py-why/EconML

    A Python package for estimating heterogeneous treatment effects from observational data by combining machine learning with econometrics for automated causal inference.

  • Project
    py-why/dowhy

    DoWhy is a Python library for end‑to‑end causal inference. It lets you define a causal graph, automatically identifies the causal effect, estimates it with a variety of statistical methods, and runs refutation tests to check robustness. The library also supports graphical causal models for root‑cause analysis, counterfactuals, and interventional sampling. Install via `pip install dowhy` and follow the four‑step workflow (model → identify → estimate → refute).

  • Project
    pymc-labs/CausalPy

    CausalPy is a Python library for Bayesian‑first causal inference in quasi‑experimental settings. It implements methods such as difference‑in‑differences, synthetic control, regression discontinuity, and instrumental variables, offering posterior‑based effect summaries, credible intervals, ROPE analysis, and publication‑quality plots. The package builds on PyMC 6, works with Python 3.12+, and provides both Bayesian and OLS options for estimation.

  • Project
    microsoft/responsible-ai-toolbox

    A suite of model and data exploration tools that enable developers to identify errors, assess fairness, and interpret AI model predictions for more responsible deployment.