Are We Overconfident in the Belief That Probability Forecasters Are Overconfident

Abstract This article provides an alternative explanation for the apparent overconfidence of subjective probability forecasters in empirical calibration experiments. This explanation, the inevitable regression-to-the-mean phenomenon expected in any random process, has nothing to do with overconfidence in the dictionary sense of that word. The article suggests that researchers have been too strong in their conclusions about the overconfidence of probability forecasters.