The Forecasting Proficiency Test: A General Use Assessment of Forecasting Ability

How can we identify accurate forecasters? Current gold standard approaches draw from two sources of information: simple cognitive assessments of reasoning ability and past forecasting accuracy. Cognitive assessments are well-studied and normed psychometric instruments, but have lower predictive value. Real-world forecasting problems are more challenging to norm a priori: they typically require a large comparison sample of forecasters to make predictive inferences. This paper develops the Forecasting Proficiency Test (FPT): a one-hour test that predicts more than 60% of the variation in out-of-sample forecasting accuracy, double the predictive utility of prior work. We highlight several key results: (1) Eliciting forecasts in a quantile format is considerably more psychometrically reliable, meaning it is more efficient at reducing measurement error about forecasters' expected accuracy with fewer items, than forecasts elicited using the standard probability format common to most judgmental forecasting tournaments. (2) Several cognitive tasks, novel to forecasting research, are highly predictive of forecasting ability. These include denominator neglect, Bayesian updating, and adherence to decision rules. (3) Although our methods do best at separating out the worst forecasters from the population, they are also remarkably effective at identifying elite talent in the upper range of the skill distribution.