Journal Article

Are forecasting models usable for policy analysis?


Abstract: In this article, Christopher A. Sims argues the answer to his title is yes. Sims explains that any decisionmaking model must incorporate some identifying assumptions to enable it to forecast the effects of alternative decisions. He argues that although all identifying assumptions in econometric policymaking models are of uncertain validity, those incorporated in vector autoregression (VAR) forecasting models have the advantage of allowing their uncertainty to be measured. Sims concludes by demonstrating a method for identifying a small macroeconomic VAR model so that it can be used to analyze monetary policy

Keywords: Forecasting; Economic policy;

Access Documents

Authors

Bibliographic Information

Provider: Federal Reserve Bank of Minneapolis

Part of Series: Quarterly Review

Publication Date: 1986

Volume: 10

Issue: Win

Pages: 2-16