Forecasting with Feedback

TL;DR

This paper proposes that forecast bias can be optimal when forecasts influence policy decisions and feedback effects are present, challenging traditional views of forecast rationality.

Contribution

It introduces a model explaining how feedback from policy decisions can lead to systematically biased yet optimal forecasts under quadratic loss.

Findings

Forecast bias can be rational in feedback environments.

Traditional tests of forecast rationality may be misleading.

Greenbook inflation forecasts exhibit properties consistent with feedback effects.

Abstract

Systematically biased forecasts are typically interpreted as evidence of forecasters' irrationality and/or asymmetric loss. In this paper we propose an alternative explanation: when forecasts inform policy decisions, and the resulting actions affect the realisation of the forecast target itself, forecasts may be optimally biased even under quadratic loss. The result arises in environments in which the forecaster is uncertain about the policymaker's reaction to the forecast, which is presumably the case in most applications. We motivate our theory by reviewing some stylised properties of Greenbook inflation forecasts. Our results point out that the presence of policy feedback poses a challenge to traditional tests of forecast rationality.