Statistical evidence is the subject of a heated and ongoing debate. Courts and legal scholars often view statistical evidence with suspicion, treating it as inadmissible even when it is probabilistically equivalent to individualized evidence. But attempts to vindicate the suspicion or to dismantle it altogether have been largely unsuccessful. The aim of this Article is to provide a comprehensive answer to the statistical evidence debate. The Article offers a novel explanation for the suspicion toward statistical evidence, pointing to the epistemic inferiority of statistical evidence due to its lack of “Sensitivity”—namely, the requirement that a belief be counterfactually sensitive to the truth as a necessary condition of “Knowledge.” After exposing the epistemic distinctions between statistical and individualized evidence, the Article turns to examining their implications for the legal arena. It claims that while the epistemic story provides an explanation for the suspicion toward statistical evidence, it does not provide a justification for this suspicion, for Sensitivity (like epistemology more generally) is not significant in the legal arena. Instead, this Article proposes an incentive-based vindication of the reluctance to use statistical evidence in court and points to the interesting interaction between the epistemic and the incentive-based approaches. After laying down the theoretical foundation, this Article demonstrates its descriptive potential. It demonstrates the proposed theory’s capacity to explain the prevailing legal doctrine and the rules governing the admissibility and sufficiency of statistical evidence across various categories, including DNA evidence and propensity-for-crime evidence as well as incriminating versus exonerating statistical evidence. On the prescriptive front, the Article provides criteria for legal reform and suggests that the admissibility of statistical evidence should be contingent on the type of offense or misconduct alleged against the defendant.