Summary: It is customary to distinguish experimental from purely observational sciences. The former include physics and molecular biology, the latter astronomy and palaeontology. Surprisingly, mainstream philosophy of science has had rather little to say about the observational/experimental distinction. For example, discussions of confirmation usually invoke a notion of ‘evidence’, to be contrasted with ‘theory’ or ‘hypothesis’; the aim is to understand how the evidence bears on the hypothesis. But whether this ‘evidence’ comes from observation or experiment generally plays no role in the discussion; this is true of both traditional and modern confirmation theories, Bayesian and non-Bayesian. In this article, the author sketches one possible explanation, by suggesting that observation and experiment will often differ in their confirmatory power. Based on a simple Bayesian analysis of confirmation, Okasha argues that universal generalizations (or ‘laws’) are typically easier to confirm by experimental intervention than by pure observation. This is not to say that observational confirmation of a law is impossible, which would be flatly untrue. But there is a general reason why confirmation will accrue more easily from experimental data, based on a simple though oft-neglected feature of Bayesian conditionalization.
Comment: Previous knowledge of Bayesian conditioning might be needed. The article is suitable for postgraduate courses in philosophy of science focusing in the distinction between observational and experimental science.