I argue that there are such things as nomological probabilities—probabilities that play a
certain explanatory role with respect to stable, long-run relative frequencies. Indeed, I argue,
we should be willing to accept nomological probabilities even if they turn out to be
metaphysically weird or even wholly sui generis entities. I then give an example of one way
in which this argument should shape future work on the metaphysics of chance by describing
a challenge to a common group of analyses of objective probability—Humean analyses—
understood as analyses of nomological probability.