We seek scientific laws that adequately account for what we have observed in the belief that, next time a similar situation arises, they will account for what we then observe. We formulate our laws in probability terms because there is always a residuum of uncertainty in our predictions; and we weigh our laws in likelihood terms because there is always a residuum of uncertainty about them. Ramsey (1931) wrote ‘In choosing a system we have to compromise between two principles: subject always to the proviso that the system must not contradict any facts we know, we choose (other things being equal) the simplest system, and (other things being equal) we choose the system which gives the highest chance to the facts we have observed. This last is Fisher's “Principle of Maximum Likelihood”, and gives the only method of verifying a system of chances.’ It is the inequality of ‘other things’ to which we must now pay attention.