Modeling Probability Forecasts via Information Diversity

TL;DR

This paper introduces a new model for aggregating expert probability forecasts that accounts for information diversity and overlap, providing a more principled approach to extremizing combined predictions.

Contribution

It presents a novel framework modeling heterogeneity from information sources in expert forecasts, improving understanding of extremizing practices.

Findings

Model describes information heterogeneity with interpretable parameters

Optimal extremizing depends on experts' information overlap

Provides insights into when to extremize forecast averages

Abstract

Randomness in scientific estimation is generally assumed to arise from unmeasured or uncontrolled factors. However, when combining subjective probability estimates, heterogeneity stemming from people's cognitive or information diversity is often more important than measurement noise. This paper presents a novel framework that models the heterogeneity arising from experts that use partially overlapping information sources, and applies that model to the task of aggregating the probabilities given by a group of experts who forecast whether an event will occur or not. Our model describes the distribution of information across experts in terms of easily interpretable parameters and shows how the optimal amount of extremizing of the average probability forecast (shifting it closer to its nearest extreme) varies as a function of the experts' information overlap. Our model thus gives a more principled understanding of the historically ad hoc practice of extremizing average forecasts.