摘要：We apply a bootstrap test to determine whether some forecasters are able to make superior probability assessments to others. In contrast to some findings in the literature for point predictions, there is evidence that some individuals really are better than others. The testing procedure controls for the different economic conditions the forecasters may face, given that each individual responds to only a subset of the surveys. One possible explanation for the different findings for point predictions and histograms is explored: that newcomers may make less accurate histogram forecasts than experienced respondents given the greater complexity of the task.
