Interesting results - but are they valid?

QCA’s grasp on causation is often questioned from a probabilistic, experimental understanding of validity. QCA results however rely on logical and set-theoretical inferences. Is a difference in languages enough to justify a separate validity yardsticks? And what secures that QCA is delivering valid results? The review of quantitative and qualitative exemplary yardsticks shows that traditions share validity concerns, yet give them different contents. The article argues that such difference is legitimized by the special assumptions about causation that inform their research processes. It therefore clarifies QCA causal ontology, identifies its special threats, and evaluates the strategies in use to prevent or tackle them - also adding a new one to address over-specified hypotheses. In this, the nomothetic yardstick proves to be a fertile framework, yet hardly a proper guideline for solutions.