AI.info
Causal inference
What would have happened otherwise — and how to defend the answer when nobody can observe it.
- Causal Inference as Decision Science
- Association, Prediction, Intervention, and Counterfactuals
- Potential Outcomes and the Fundamental Problem
- Units, Treatments, Versions, and Timing
- Estimands, Target Populations, and Effect Scales
- Identification Versus Estimation
- Causal DAGs and Assumption Maps
- Confounders, Mediators, Colliders, and Selection
- Consistency, Exchangeability, Positivity, and Interference
- Target Trials and Protocol-First Causal Design
- Randomization and Intention-to-Treat Effects
- Product A/B Testing and Instrumentation
- Power, Minimum Detectable Effects, and Sample Size
- Cluster-Randomized Experiments
- Noncompliance, Encouragement Designs, and LATE
- Attrition, Missing Outcomes, and Protocol Deviations
- Interference, Spillovers, and Network Experiments
- Multiplicity, Subgroups, and Sequential Monitoring
- Adaptive Experiments and Bandit Allocation
- The G-Formula and Standardization
- Outcome Regression and Counterfactual Model Diagnostics
- Propensity Scores and Covariate Balancing
- Matching and Subclassification
- Inverse Probability Weighting and Pseudo-Populations
- Overlap, Positivity, Trimming, and Target Redefinition
- AIPW, Orthogonal Scores, and Double Robustness
- Targeted Maximum Likelihood Estimation
- Measurement Error, Proxies, and Misclassification
- Missing Data, Selection Bias, and Observation Processes
- Sensitivity Analysis, Negative Controls, and Falsification
- Time-to-Event Outcomes, Censoring, and Competing Risks
- Observational Target-Trial Emulation
- Time-Varying Treatments and Treatment–Confounder Feedback
- Marginal Structural Models, G-Computation, and G-Estimation
- Instrumental Variables Beyond Randomized Encouragement
- Regression Discontinuity Designs
- Difference-in-Differences and Parallel Trends
- Staggered Adoption and Event-Study Designs
- Synthetic Control and Synthetic Difference-in-Differences
- Interrupted Time Series and Natural Experiments
- Heterogeneous Treatment Effects and CATE
- Meta-Learners and Uplift Modeling
- Causal Trees and Generalized Random Forests
- Double/Debiased Machine Learning
- Policy Learning and Off-Policy Evaluation
- Mediation, Direct Effects, and Mechanism Questions
- Transportability and External Validity
- Causal Discovery and Causal Representation Learning
- Distributional Effects, Equity, and Causal Reporting
- Causal Inference Capstone: Design and Defend an Intervention Study