Where probabilities come from

Ian Hacking in The Logic of Statistical Inference taught that probabilities are characterised relative to chance set-ups and do not make sense without them. My discussion is an elaboration of his claim. A chance set-up is a nomological machine for probabilistic laws, and our description of it is a model that works in the same way as a model for deterministic laws (like the Newtonian model of the planetary system that gives rise to Kepler's laws discussed in chapter 3 or the socio-economic machine of chapter 6). A situation must be like the model both positively and negatively – it must have all the relevant characteristics featured in the model and it must have no significant interventions to prevent it operating as envisaged – before we can expect repeated trials to give rise to events appropriately described by the corresponding probability.

Who is the enemy?

The view I am arguing against takes probabilities to be necessary associations between measurable quantities; and it assumes that probabilities in this sense hold not ceteris paribus but simpliciter. In particular they do not need a nomological machine to generate them. I am going to discuss here a case from economics in which it is easy to see the implausibility of a free-standing probability. It is typically objected that physics is different. We have seen in the previous chapters why I do not agree.