The Measurement and Behavior of Uncertainty: Evidence from the ECB Survey of Professional Forecasters

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractWe use matched point and density forecasts of output growth and infl ation from the ECB Survey of Professional Forecasters to derive measures of forecast uncertainty, forecast dispersion, and forecast accuracy. We construct uncertainty measures from aggregate density functions as well as from individual histograms. The uncertainty measures display countercyclical behavior, and there is evidence of increased uncertainty for output growth and infl ation since 2007. The results also indicate that uncertainty displays a very weak relationship with forecast dispersion, corroborating the fi ndings of other recent studies indicating that disagreement is not a valid proxy for uncertainty. In addition, we fi nd no correspondence between movements in uncertainty and predictive accuracy, suggesting that time-varying conditional variance estimates may not provide a reliable proxy for uncertainty. Last, using a regression equation that can be interpreted as a (G)ARCH-M-type model, we fi nd limited evidence of linkages between uncertainty and levels of infl ation and output growth.

A Closer Look at the Behavior of Uncertainty and Disagreement: Micro Evidence from the Euro Area

“…Several different methods have been used to measure uncertainty based on the reported density (histogram) forecasts. In some cases, the uncertainty measure is derived from the individual density forecasts assuming that the probability mass within each interval is concentrated at the midpoint of each interval [Rich and Tracy (2010), Kenny et al (2015)], or that the probability mass is distributed uniformly within each interval [Zarnowitz and Lambros (1987), Abel et al (2016)]. 2 In other cases, the uncertainty measure is derived by fitting a continuous distribution to the individual density forecasts, where the continuous distribution is a normal distribution [Giordani and Soderlind (2003), Boero et al (2014)], a generalized beta distribution [Bruine de Bruin et al (2011)], or both [Clements (2014a[Clements ( , 2014b].…”

“…5 Examining matched point and density forecasts, Rich and Tracy (2010) find a very weak relationship between disagreement and uncertainty for the US-SPF. Recent analyses that have examined data from other surveys featuring point and density forecasts, such as Boero et al (2008) for the BOE-SEF and Abel et al (2016) for the ECB-SPF, have found little support for the use of disagreement as proxy for uncertainty. 5 Rich and Tracy (2010) and Boero et al (2014) discuss the problematic nature of fitting normal distributions to histograms where respondents place positive probability in less than three bins.…”

Survey-based forecast distributions for Euro Area growth and inflation: ensembles versus histograms

“…Our analysis relates to a number of recent empirical studies on the ECB-SPF data (e.g., Genre et al 2013;Kenny et al 2014Kenny et al , 2015Abel et al 2016;Glas and Hartmann 2016). Compared to these studies, the main innovation of the present paper is our use of ensemble methods for constructing forecast distributions.…”

Does Uncertainty Affect Non-response to the European Central Bank’s Survey of Professional Forecasters?

“…The European Central Bank's Survey of Professional Forecasters (ECB's SPF) is gaining prominence in recent years not only for policy analysis (ECB 2014a(ECB , 2014c but also for research (Lyziak and Paloviita 2016;Glas and Hartmann 2016;Kenny and Melo Fernandes 2016;Poncela and Senra 2016;Abel et al 2015;Bowles et al 2010;Conflitti 2011;Kenny et al 2012). The SPF was launched in the first quarter of 1999 and collects expectations of inflation, GDP growth and the unemployment rate in the euro area for different forecast horizons.…”

“…Abel et al (2015) found a strong negative relationship between uncertainty and aggregate real GDP growth forecasts. They did not use individual data in their analysis.…”