Forecasts in Times of Crises

IMF Working Papers, March 9, 2018

Source details

Canonical URL

Forecasts in Times of Crises

Other formats

• Markdown version
• Structured JSON version
• Bundle manifest

Bibliographic details

• Authors: Theo S. Eicher, David J. Kuenzel, Chris Papageorgiou, Charalambos Christofides
• Published: March 9, 2018
• Series: IMF Working Papers
• DOI: https://doi.org/10.5089/9781484345436.001

Publication metadata

• Title: Forecasts in Times of Crises
• Authors: Theo S. Eicher, David J. Kuenzel, Chris Papageorgiou, Charalambos Christofides
• Date: March 9, 2018
• Series: Working Paper No. 2018/048
• Volume: 2018; Issue: 048; Pages: 33
• DOI: https://doi.org/10.5089/9781484345436.001
• Stock No: WPIEA2018048
• ISBN: 9781484345436
• ISSN: 1018-5941

Research scope and methods

• Data source: IMF’s Monitoring of Fund Arrangement (MONA) database.
• Variables analyzed: 29 macroeconomic variables assessed for bias, efficiency, and information content.
• Comparative benchmark: IMF forecasts evaluated against naive forecast approaches.

Key findings

• IMF forecasts add substantial informational value as they consistently outperform naive forecast approaches.
• Two thirds of the key macroeconomic variables examined are forecast inefficiently.
• Six variables exhibit significant forecast bias:
  • growth of nominal GDP
  • public investment
  • private investment
  • the current account
  • net transfers
  • government expenditures
• Forecasts for low-income countries are the main drivers of forecast bias and inefficiency, reflecting perhaps larger shocks and lower data quality.

Decomposition of forecast errors

• GDP growth forecast errors:
  • Forecast errors for private consumption growth are the key contributor to GDP growth forecast errors.
• Fiscal budget forecast errors:
  • Forecast errors for non-interest expenditure growth and tax revenue growth are crucial determinants of the forecast errors in the growth of fiscal budgets.
• Balance of payments forecast errors:
  • Forecast errors for balance of payments growth are significantly influenced by forecast errors in goods import growth.

Implications for forecasting and policy

• IMF forecasts contain valuable information but exhibit systematic inefficiencies and biases across many aggregates, indicating scope for methodological improvement.
• Particular aggregates requiring further attention in future forecast models for countries in crises:
  • nominal GDP growth
  • public investment and private investment growth
  • current account and net transfers
  • government expenditures
  • private consumption growth (for GDP errors)
  • non-interest expenditure growth and tax revenue growth (for fiscal errors)
  • goods import growth (for balance of payments errors)
• Special focus recommended on forecasts for low-income countries due to their outsized role in driving bias and inefficiency.

Source: IMF Working Paper "Forecasts in Times of Crises" (Working Paper No. 2018/048), March 9, 2018.

Content in this bundle

• Forecasts in Times of Crises, WP/18/48, March 2018
  • Forecasts in Times of Crises, WP/18/48, March 2018 (Markdown version)
  • Forecasts in Times of Crises, WP/18/48, March 2018 (PDF)