On the Uses and 'Abuses' of Empirical Evidence in the Death Penalty Debate

Abstract

John J. Donohue and Justin Wolfers [Uses and Abuses of Empirical Evidence in the Death Penalty Debate, Stanford Law Review, vol. 58 (2005): 791-846] critique a number of recent econometric studies purporting to demonstrate a deterrent effect of capital punishment. Donohue and Wolfers argue that the conclusions drawn from most of these studies are fundamentally flawed as their results are highly sensitive to small changes in the employed econometric specification. This paper focuses on Donohue's and Wolfers' criticism of a study by Paul R. Zimmerman [State Executions, Deterrence, and the Incidence of Murder, Journal of Applied Economics, vol. 7 (2004): 163-193]. It is shown that Donohue and Wolfers make a number of misrepresentations and errors in assessing the results and conclusions put forward in Zimmerman's analysis, and as such, their criticisms of the latter are effectively vacuous. And although Zimmerman's ultimate conclusions regarding the deterrent effect of capital punishment are not fundamentally different from Donohue's and Wolfers', the latter authors' comprehensive review of recent death penalty studies (as well as their admonishments concerning the use of potentially fragile empirical models to inform policy decisions) marks their paper as an important contribution to the literature.

Keywords: capital punishment, death penalty, deterrence, executions, statistical inference

JEL Classification: K42