Member-only story
Understanding Independence and Why It Is Critical in Causal Inference and Causal Validation
A step-by-step guide to understanding the concept of independence and how to apply it to validate directed acyclic graphs in causal validation using Python
Background
In a recent article the author explored and explained how the concept of dependence can be used to validate a proposed Directed Acyclic Graph (DAG) against a dataset to identify spurious edges in the graph i.e. causal links suggested by the DAG that do not exist in the data.
In this second instalment, the opposite (but equally critical) concept will be applied i.e. how to use independence to identify missing edges. These are causal links that do not appear in the proposed DAG but do actually exist in the data that must be added back into the DAG to make it complete and correct.
Introduction
Causal Inference is an emergent branch of data science concerned with determining the cause-and-effect relationship between events and outcomes and it has the potential to significantly add to the value that machine learning can generate for organisations.
