Bayesian aggregation of two forecasts in the partial information framework

TL;DR

This paper introduces a method for combining two forecasts using Gaussian aggregation without the need for parameter estimation, providing an explicit formula for a one-shot aggregation scenario.

Contribution

It generalizes previous results by removing the requirement for parameter estimation and offers a direct formula for aggregating two forecasts in the partial information framework.

Findings

Derived an explicit Gaussian aggregator formula for two forecasters.

Extended previous models to settings without parameter estimation.

Facilitated one-shot forecast aggregation in partial information scenarios.

Abstract

We generalize the results of \cite{SPU, SJPU} by showing how the Gaussian aggregator may be computed in a setting where parameter estimation is not required. We proceed to provide an explicit formula for a "one-shot" aggregation problem with two forecasters.