Averaging impulse responses using prediction pools

• 成果类型: Article
• 署名作者: Ho, Paul; Lubik, Thomas A.; Matthes, Christian
• 署名单位: Federal Reserve System - USA; Federal Reserve Bank - Richmond; Indiana University System; Indiana University Bloomington
• 刊物名称: JOURNAL OF MONETARY ECONOMICS
• ISSN/ISSBN: 0304-3932
• DOI: 10.1016/j.jmoneco.2024.103571
• 发表日期: 2024
• 关键词: Prediction pools; model averaging; impulse responses; misspecification

摘要

Macroeconomists construct impulse responses using many competing time series models and different statistical paradigms (Bayesian or frequentist). We adapt optimal linear prediction pools to efficiently combine impulse response estimators for the effects of the same economic shock from this vast class of possible models. We thus alleviate the need to choose one specific model, obtaining weights that are typically positive for more than one model. Our Monte Carlo simulations and empirical applications illustrate how the weights leverage the strengths of each model by (i) trading off properties of each model depending on variable, horizon, and application and (ii) accounting for the full predictive distribution rather than being restricted to specific moments.1 1