Lewis’s counterfactual analysis of causation starts with the claim that c causes e if ~ C > ~ E, where c and e are events, C and E are the propositions that c and e respectively occur, ~ is negation and > is the counterfactual conditional. The purpose of my project is to provide a counterfactual analysis of causation which departs signigicantly from Lewis’s starting point, and thus can hope to solve several stubborn problems for that approach. Whereas Lewis starts with a sufficiency claim, my analysis claims that a certain counterfactual is necessary for causation. I say that, if c causes e, then ~ E > ~ C — I call the latter the Reverse Counterfactual. This will often, perhaps always, be a backtracking counterfactual, so two chapters are devoted to defending a conception of counterfactuals which allows backtracking. Thus prepared, I argue that the Reverse Counterfactual is true of causes, but not of mere conditions for an effect. This provides a neat analysis of the principles governing causal selection, which is extended in a discussion of causal transitivity. Standard counterfactual accounts suffer counterexamples from preemption, but I argue that the Reverse Counterfactual has resources to deal neatly with those too. Finally I argue that the Reverse counterfactual, as a necessary condition on causation, is the most we can hope for: in principle, there can be no counterfactual sufficient condition for causation.