Learning Together Slowly: Bayesian Learning about Political Facts

Although many studies suggest that voters learn about political facts with prejudice toward their preexisting beliefs, none have fully characterized all inputs to Bayes' Rule, leaving uncertainty about the magnitude of bias. This paper evaluates political learning by first highlighting the importance of careful measures of each input and then presenting a statistical model and experiment that measure the magnitude of departure from Bayesian learning. Subjects learn as cautious Bayesians, updating their beliefs at about 73% of perfect application of Bayes' Rule. They are also modestly biased. For information consistent with prior beliefs, subject learning is not statistically distinguishable from perfect Bayesian. Inconsistent information, however, corresponds to learning less than perfect. Despite bias, beliefs do not polarize. With small monetary incentives for accuracy, aggregate beliefs converge toward common truth. Cautious Bayesian learning appears to be a reasonable model of how citizens process political information.