Systematizing Macroframework Forecasting: High-Dimensional Conditional Forecasting with Accounting Identities
IMF Working Papers, June 3, 2022
Source details
- Canonical URL
- Systematizing Macroframework Forecasting: High-Dimensional Conditional Forecasting with Accounting Identities
Other formats
Bibliographic details
- Authors: Sakai Ando, Taehoon Kim
- Published: June 3, 2022
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9798400211683.001
Summary
- Forecasting a macroframework composed of many macroeconomic variables and accounting identities is widely conducted in the policy arena to present an economic narrative and check its consistency.
- The paper identifies the core challenge: forecasters must extend limited information to the entire macroframework in an internally consistent manner.
- The paper proposes a method that can improve the WEO forecast.
Methodology proposed
- Integrate (1) conditional forecasting with machine-learning techniques and (2) forecast reconciliation of hierarchical time series.
- Emphasis on systematizing macroframework forecasting to handle high-dimensional conditional forecasting while respecting accounting identities.
Applications and empirical findings
- Applied to an advanced economy and a tourism-dependent economy using France and Seychelles.
- The application shows that the proposed method can improve the WEO forecast.
Key publication information and metadata
- By Sakai Ando, Taehoon Kim
- June 3, 2022
- Pages: 25
- Volume: 2022
- Issue: 110
- Series: Working Paper No. 2022/110
- DOI: https://doi.org/10.5089/9798400211683.001
- Stock No: WPIEA2022110
- ISBN: 9798400211683
- ISSN: 1018-5941
- Subject: Balance of payments, Current account balance, GDP measurement, National accounts
- Keywords: Accounting Identities, accounting identity, Conditional Forecasting, Current account balance, forecasting method, framework forecasting, GDP measurement, Hierarchical Time Series, IMF working paper 22/110, Macroframework, Reconciliation, unknown variable
IMF Working Papers — Systematizing Macroframework Forecasting: High-Dimensional Conditional Forecasting with Accounting Identities (June 3, 2022) by Sakai Ando and Taehoon Kim.
Content in this bundle
- Working Paper