BIROn - Birkbeck Institutional Research Online

    R2 bounds for predictive models: what univariate properties tell us about multivariate predictability

    Mitchell, J. and Robertson, D. and Wright, Stephen (2017) R2 bounds for predictive models: what univariate properties tell us about multivariate predictability. Journal of Business and Economic Statistics , ISSN 0735-0015. (In Press)

    [img]
    Preview
    Text
    final submitted jbes paper.pdf - Author's Accepted Manuscript

    Download (3MB) | Preview

    Abstract

    A longstanding puzzle in macroeconomic forecasting has been that a wide varietyof 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 R2 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.

    Metadata

    Item Type: Article
    Additional Information: This is an Accepted Manuscript of an article published by Taylor & Francis, available online at the link above.
    Keyword(s) / Subject(s): Forecasting, Macroeconomic Models, Autoregressive Moving Average Representations; Predictive Regressions; Nonfundamental Representations; Time-Varying ARMA; Inflation Forecasts JEL codes: C22, C32, C53, E37
    School: Birkbeck Schools and Departments > School of Business, Economics & Informatics > Economics, Mathematics and Statistics
    Depositing User: Stephen Wright
    Date Deposited: 17 Jan 2018 15:01
    Last Modified: 23 Dec 2018 01:10
    URI: http://eprints.bbk.ac.uk/id/eprint/20883

    Statistics

    Downloads
    Activity Overview
    34Downloads
    127Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item