Causal Inference and Discovery in Python

2

Judea Pearl and the Ladder of Causation

In the last chapter, we discussed why association is not sufficient to draw causal conclusions. We talked about interventions and counterfactuals as tools that allow us to perform causal inference based on observational data. Now, it’s time to give it a bit more structure.

In this chapter, we’re going to introduce the concept of the Ladder of Causation. We’ll discuss associations, interventions, and counterfactuals from theoretical and mathematical standpoints. Finally, we’ll implement a couple of structural causal models in Python to solidify our understanding of the three aforementioned concepts. By the end of this chapter, you should have a firm grasp of the differences between associations, interventions, ...