An Evaluation of World Economic Outlook Growth Forecasts, 2004–17

IMF Working Papers, August 6, 2021

Source details

Canonical URL: An Evaluation of World Economic Outlook Growth Forecasts, 2004–17

The paper examines the performance of World Economic Outlook (WEO) growth forecasts for 2004-17.
Short-term real GDP growth forecasts over 2004-17:
- Exhibit little bias.
- Have accuracy broadly similar to those of Consensus Economics forecasts.
Two- to five-year ahead WEO growth forecasts in 2004-17:
- Tend to be upward biased.
- In up to half of countries, are less accurate than a naïve forecast given by the average growth rate in the recent past.
The analysis indicates that more efficient use of available information can improve forecast accuracy for some economies.

Internal and external information identified as relevant for improving forecasts includes:
- The estimated output gap.
- Projected terms of trade.
- The growth forecasts of major trading partners.
Relative performance notes:
- Short-term horizon: little bias and comparable accuracy to Consensus Economics.
- Medium-term horizon (two- to five-year): systematic upward bias and frequent underperformance versus naïve historical-average forecasts.

Enhance the use of available internal and external indicators in forecast models, specifically:
- Incorporate the estimated output gap more effectively.
- Integrate projected terms of trade into growth projections.
- Use the growth forecasts of major trading partners to inform medium-term forecasts.
For economies where two- to five-year forecasts underperform, consider benchmarking against simple historical-average forecasts as a robustness check.

IMF Working Paper — An Evaluation of World Economic Outlook Growth Forecasts, 2004–17