Search
Close
Search
Advanced Search
Search Menu
AI Discovery Assistant

Abstract

Empirical studies using survey data on expectations have frequently observed that forecasts are biased and have concluded that agents are not rational. We establish that existing rationality tests are not robust to even small deviations from symmetric loss and hence have little ability to tell whether the forecaster is irrational or the loss function is asymmetric. We quantify the trade-off between forecast inefficiency and asymmetric loss leading to identical outcomes of standard rationality tests and explore new and more general methods for testing forecast rationality jointly with flexible families of loss functions that embed squared loss as a special case. Empirical applications to survey data on forecasts of real output growth and inflation suggest that rejections of rationality may largely have been driven by the assumption of squared loss. Moreover, our results suggest that agents are averse to “bad” outcomes such as lower-than-expected real output growth and higher-than-expected inflation and that they incorporate such loss aversion into their forecasts.

This content is only available as a PDF.
© 2008 by the European Economic Association
JEL
C22 - Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes C53 - Forecasting and Prediction Methods; Simulation Methods E37 - Forecasting and Simulation: Models and Applications
Issue Section:
Articles
You do not currently have access to this article.
Download all slides