R2 Bounds for Predictive Models: What Univariate Properties Tell us About Multivariate Predictability. Issue 4 (2nd October 2019)

• Record Type: Journal Article
• Authors: Mitchell, James; Robertson, Donald; Wright, Stephen
• Is Part Of: Journal of business & economic statistics. Volume 37:Issue 4(2019)
• Page Start: 681
• Page End: 695
• Publication Date: 2019-10-02
• Subjects: Autoregressive moving average representations -- Forecasting -- Macroeconomic models -- Nonfundamental representations -- Predictive regressions -- Time-varying ARMA; Economics -- Statistical methods -- Periodicals; Commercial statistics -- Periodicals; Économie politique -- Méthodes statistiques -- Périodiques; Statistique commerciale -- Périodiques; 330.015195
• DOI: 10.1080/07350015.2017.1415909
• Languages: English
• ISSNs: 0735-0015

Abstract

ABSTRACT: A long-standing puzzle in macroeconomic forecasting has been that a wide variety of multivariate models have struggled to out-predict univariate models consistently. We seek an explanation for this puzzle in terms of population properties. We derive bounds for the predictive R 2 of the true, but unknown, multivariate model from univariate ARMA parameters alone. These bounds can be quite tight, implying little forecasting gain even if we knew the true multivariate model. We illustrate using CPI inflation data. Supplementary materials for this article are available online.