Open Collections

Abstract

I discuss the implications of Simpson’s paradox for epistemology and decision theory. In Chapter One I outline the paradox, focussing on its identification, nature, and type of reasoning that it involves. In Chapter Two I discuss the view that Simpson’s paradox is resolved by means of graph-based causal analysis. In Chapter Three I outline a major problem (hitherto unacknowledged) that Simpson’s paradox poses for the probabilistic Bayesian theory of evidence. I make a proposal to split the probabilistic concept of evidence into a causal and a news-value kind of evidence, tracking causal probabilities under an intervention, and tracking overall probabilistic relevance under conditioning. In Chapters Four and Five I apply the proposal to two further areas of concern. In Chapter Four I defend a unified causal view of Simpson’s paradox. In Chapter Five I defuse a problem about counterfactual force of evidence. In Chapters Six and Seven I discuss Simpson’s paradox and the sure thing principle in decision theory. I then conclude in Chapter Eight.