ABSTRACT
Analogies hinge on similarity-relations. Unfortunately, the only thing that is clear about similarity is what it is not. It is not what 'egalitarians' like John Stuart Mill take it to be. They simply construct the degree of similarity between two objects as a function of the number of shared and nonshared features. The problems with this theory are well-known and need not be rehearsed here. Any two objects have indefinitely many features in common, and indefinitely many features in which they differ. Bare similarity is too unconstrained to be of any use; we need a criterion for relevant similarity.
