Content text 2.3 Causal Inference.pdf
pacmann.io © 2022 – Pacmann AI 22 Causal Inference
pacmann.io © 2022 – Pacmann AI 23 Causal Inference ● If we have a correlation, we can we tell if it is causation by doing the causal inference ● Let’s try to think about whether some X causes Y that is, if we manipulated X, then Y would change as a result ● For simplicity, let’s assume that X is either 1 or 0 X = 1 = got a medical treatment X = 0 = didn't got a medical treatment 🚫
pacmann.io © 2022 – Pacmann AI 24 Causal Inference ● Let’s consider just one person - Angela. ● Check what Angela’s {Y} is when we make X=0, ● Then, check what Angela’s {Y} is again when we make X=1. X = 1 X = 0 Y = Angela’s Condition Y = Angela’s Condition 🚫
pacmann.io © 2022 – Pacmann AI 25 Causal Inference ● Are those two Ys different? If so, X causes Y! X = 1 X = 0 Y = 1 Y = 0 Causal Effect 🚫