Causality and Unification: How Causality Unifies Statistical Regularities

Two key ideas of scientific explanation −explanation as causal information and explanation as unification– have frequently been set into mutual opposition. This paper proposes a “dialectical solution” to this conflict, by arguing that causal explanations are preferable to non-causal ones, because they lead to a higher degree of unification at the level of explaining statistical regularities. The core axioms of the theory of causal nets (TC) are justified because they offer the best if not the only unifying explanation of two statistical phenomena: screening off and linking up. Alternative explanations of the two phenomena are discussed and it is shown why they don’t work. It is demonstrated that although the core axioms of TC are empirically vacuous, extended versions of TC have empirical content by means of which they can generate independently testable