A causation coefficient and taxonomy of correlation/causation\n relationships

This paper introduces a causation coefficient which is defined in terms of\nprobabilistic causal models. This coefficient is suggested as the natural\ncausal analogue of the Pearson correlation coefficient and permits comparing\ncausation and correlation to each other in a simple, yet rigorous manner.\nTogether, these coefficients provide a natural way to classify the possible\ncorrelation/causation relationships that can occur in practice and examples of\neach relationship are provided. In addition, the typical relationship between\ncorrelation and causation is analyzed to provide insight into why correlation\nand causation are often conflated. Finally, example calculations of the\ncausation coefficient are shown on a real data set.\n