Economic Forecasters’ Uncertainty vs. Disagreement

By Gerardo Manzo and Jeffrey N. Saret on August 23, 2016
Janet Yellen Talking to another member of the federal Reserve

Fed and ECB data shows that the level of disagreement across forecasters today is within the historical norm, but uncertainty appears higher than ever, particularly in Europe.

By disentangling disagreement from uncertainty in polls of forecasters, asset allocators can draw a much clearer picture of what the data says and potentially hedge their exposures accordingly. For example, if half of polled experts believe with high conviction that one outcome appears likely, and the other half believe equally firmly that the opposite outcome appears likely, an asset allocator might want to hedge against two discrete scenarios. Alternatively, if all forecasters share a common expected outcome, but each feels highly uncertain of that outcome, an asset allocator might want to hedge against a broader range of scenarios.

One can infer more than just the means from the surveys of professional forecasters by studying both the disagreement and the uncertainty of the forecasts. Consistent with academic research, disagreement equals the inter-quartile range (75th minus 25th percentile) of point forecasts, whereas uncertainty equals the average of the individual variances from each forecaster’s probability distribution of outcomes.1 Figure 1 depicts these two measures.

Uncertainty and disagreement in real growth and inflation in Europe and the US

For GDP and inflation forecasts, data from the US Federal Reserve and the European Central Bank reveals two interesting findings.  First, both US and European forecasters currently disagree with each other about as much as usual on growth and inflation. However, the level of uncertainty for each forecaster appears higher today than at any other time during the past 15 years, particularly in Europe. Asset allocators might want to incorporate that uncertainty when hedging their economic risk.

Download PDF — 1.20 MB
Footnotes

1. Academic research, including Kajal and Sheng (2010), Rich and Tracy (2010), and Borea, Smith, and Walls (2015), applies similar approaches.

The views expressed above are not necessarily the views of Two Sigma Investments, LP or any of its affiliates (collectively, “Two Sigma”).  The information presented above is only for informational and educational purposes and is not an offer to sell or the solicitation of an offer to buy any securities or other instruments. Additionally, the above information is not intended to provide, and should not be relied upon for investment, accounting, legal or tax advice. Two Sigma makes no representations, express or implied, regarding the accuracy or completeness of this information, and the reader accepts all risks in relying on the above information for any purpose whatsoever.  For other important disclaimers and disclosures, download the full article.