π Language: English | νκ΅μ΄ β
Why Should We Care About Causal Inference?ΒΆ
Through counterfactuals and potential outcomes, explains why correlation isn't causation β and how RCTs solve it.
Regression Discontinuity Design (RDD)ΒΆ
Introduces regression discontinuity design and how cutoff-based assignment can support causal comparison near a threshold.
Fuzzy RDDΒΆ
When the cutoff no longer fully determines treatment, this video shows how the Wald estimator and 2SLS recover the local average treatment effect (LATE) for compliers.
Inverse Probability Weighting (IPW)ΒΆ
Introduces the core idea of IPW: correcting for confounding by weighting samples by the inverse of their treatment probability to estimate treatment effects.