The Paradox of Unbiased Public Information

Abstract

Recent game-theoretic literature on juries proposes many reforms including the abandonment of the unanimity rule. Considering the scope of the proposed change, this paper sets out to do one thing: it tests the critical game-theoretic assumption that jurors vote on the basis of being pivotal. The test is devised such that if the groups do well in aggregating dispersed information, they would support the game-theoretic view of juries; if not, they would oppose the game-theoretic view. Here is how. In theory, as shown in the paper, large enough juries remain relatively unaffected when public signals the jurors observe happen to be misleading because theoretical juries do not erroneously overweight the public signals at the expense of the private signals. In reality, however, each individual may overweight misleading public signals leading real juries to a terrible outcome. It is this potential for direct contradiction between theoretical and experimental juries that makes our experimental test sharper than previous tests: given misleading public signals, rational voting would still produce information aggregation; naïve voting would not. In prior research with no public signals, both rational and naïve voting produced information aggregation. Hence, we present a sharper test. Certain public policy implications of our work pertaining to the media are offered.