Causation and Correlation with Probabilistic Causal Models

A causation coefficient and taxonomy of correlation/causation relationships

This paper introduces a causation coefficient which is defined in terms of probabilistic causal models.This coefficient is suggested as the natural causal analogue of the pearson correlation coefficient and permits comparingcausation and correlation to each other in a simple, yet rigorous manner.Examples of the possible correlation/causation relationships that can occur in practice are provided and the typical relationship between correlation and causation is analyzed to provide insight into why correlationand causation are often conflated.Example calculations of the coefficient are shown on a real data set.Correlation and causation are often conflated in practice.This paper introduces a causation coefficient which is defined in terms of probabilistic causal models.This coefficient is suggested as the natural causal analogue of the pearson correlation coefficient and permits comparingcausation and correlation to each other in a simple, yet rigorous manner.Examples of the possible correlation/causation relationships that can occur in practice are provided and the typical relationship between correlation and causation is analyzed to provide insight into why correlationand causation are often conflated.Correlation and causation are often conflated in practice.This paper introduces a causation coefficient which is defined in terms of probabilistic causal models.