Getting Started
User Guide
Examples
dowhy package
Contributing
Release notes
Citing this package
v0.10
Releases
v0.9.1
v0.9
v0.8
v0.7.1
v0.7
v0.6
v0.5.1
v0.5
v0.4
v0.2
v0.1.1-alpha
Branches
main
Foreword
Introduction to DoWhy
Modeling Causal Relations
Specifying a causal graph using domain knowledge
Learning causal structure from data
Refuting a Causal Graph
Performing independence tests
Graph refutations
Modeling Graphical Causal Models (GCMs)
Types of graphical causal models
Generate samples from a GCM
Customizing Causal Mechanism Assignment
Estimating Confidence Intervals
Performing Causal Tasks
Estimating Causal Effects
Identifying causal effect
Backdoor criterion
Frontdoor criterion
Natural experiments and instrumental variables
ID algorithm for discovering new identification strategies
Estimating average causal effect using backdoor
Regression-based methods
Distance-based matching
Propensity-based methods
Do-sampler
Estimating average causal effect with natural experiments
Estimating conditional average causal effect
Estimating average causal effect using GCM
Estimating direct and indirect effects
Estimating natural direct and indirect effects
Direct Effect: Quantifying Arrow Strength
Explaining Observed Effects and Root-Cause Analysis
Anomaly Attribution
Attributing Distributional Changes
Quantifying Intrinsic Causal Influence
Unit Change Attribution
Feature Relevance
Asking and Answering What-If Questions
Simulating the Impact of Interventions
Computing Counterfactuals
Predicting outcome for out-of-distribution inputs
Refuting causal estimates
Refuting Effect Estimates
Placebo Treatment Refuter
Dummy Outcome Refuter
Random Common Cause Refuter
Data Subsample Refuter
Sensitivity Analysis
Simulation-based sensitivity analysis
Partial-R2 based sensitivity analysis for linear estimators
Reisz estimator-based sensitivity analysis for non-linear estimators
Citing this package
Unit Change Attribution
TBD