The Article argues that the economic analysis of tort law has yet to satisfactorily answer a critical threshold question: which of the many inputs that lead to an accident should be included in a court’s liability analysis? As a result of this missing theory, the economic analysis of tort law provides indeterminate prescriptions. The Article shows how three separate areas of the literature can be seen as being about the general problem of which variables to include in the liability test and the tension between short- and long-run optima. The Article proposes an analytical framework—a continuum from short to long run—to understand the problem and show the way in which courts have crafted tort law doctrines to address the issue. Finally, the Article concludes that no satisfactory general theory is possible and that the optimal combination of liability rules will depend upon empirical questions about specific accident contexts.