The Relation Between Overreaction in Forecasts and Uncertainty: A Nonlinear Approach

This paper examines overreaction of oil price forecasters. It takes into account impacts of uncertainty, measured by VSTOXX volatility; noisy signals, measured by oil price volatility; and oil price return on forecast changes. The panel smooth transition regression model is applied with different specifications of the transition function to account for nonlinear relations. Data on oil price expectations for different time horizons are taken from the European Central Bank Survey of Professional Forecasters. The results show that forecast changes are governed by overreaction. However, overreaction is markedly reduced when high levels of uncertainty prevail. On the other hand, noisy signals and positive oil price return tend to cause higher overreaction.