https://kobybibas.github.io/tags/causal-inference/Recent content in Causal Inference on Koby BibasHugo -- gohugo.ioenMon, 28 Sep 2026 00:00:00 +0000https://kobybibas.github.io/posts/20260928_estimating_a_treatment_effect/summary/Mon, 28 Sep 2026 00:00:00 +0000https://kobybibas.github.io/posts/20260928_estimating_a_treatment_effect/summary/Intro Machine learning models predict by the correlation between features and labels. For an outcome under a different treatment, that correlation can give the wrong answer. Consider the following example. We have three samples: one got treatment \(T=0\), and two got treatment \(T=1\). sample treatment \(T\) Observed outcome \(Y\) \(Y(0)\), had they received \(T=0\) \(Y(1)\), had they received \(T=1\) 1 0 9 9 12 2 1 3 0 3 3 1 3 0 3 A naive way to measure whether treatment \(T=1\) or \(T=0\) is more helpful: