Parsimony and Causality

Sufficient and necessary conditions--the primary search targets of Boolean (or set-theoretic) methods of causal inference--tend to feature redundant elements, i.e. factors such that, if they are eliminated from solution formulas, the remaining conditions are still sufficient and/or necessary for corresponding outcomes. For the methodological framework of QCA, Ragin and Sonnett (2005) distinguish three different strategies researchers may adopt when eliminating redundant elements from Boolean solution formulas. In case of limitedly diverse data, only the most liberal strategy is able to eliminate all redundancies. Yet, as this elimination strategy typically requires a host of counterfactual simplifying assumptions, which are often difficult to justify, it has recently become common practice in QCA studies to settle for so-called intermediate solutions formulas with some redundant elements (cf. Ragin 2008, ch. 9; Schneider and Wagemann 2012, ch. 6). This is usually legitimized with recourse to principles as Occam's Razor, relative to which parsimony is a mere pragmatic virtue of causal models. This paper argues that intermediate solution formulas cannot be causally interpreted. Subject to e.g. Mackie's (1974) INUS-theory of causation, to which representatives of QCA explicitly subscribe (cf. e.g. Mahoney and Goertz 2006), causes are Boolean difference-makers for their effects. Yet, elements of solutions formulas that can be eliminated without relationships of sufficiency and necessity thereby being affected make no difference to corresponding outcomes and, thus, they do not cause the latter. That is, parsimony of solution formulas is much more than a mere pragmatic virtue of causal models; rather, there exists a tight conceptual connection between parsimony and causality. Only maximally parsimonious solutions formulas represent causal structures. That is, researchers that want to uncover conditions that causally contribute to scrutinized outcomes must not content themselves with intermediate solutions formulas. Or differently, the common practice of settling for intermediate solution formulas is not theoretically warranted.