Eric Hillebrand

Bagging Weak Predictors

Publikation: Working paperForskning

Dokumenter

  • rp14_01

    Indsendt manuskript, 704 KB, PDF-dokument

Relations between economic variables can often not be exploited for forecasting, suggesting that predictors are weak in the sense that estimation uncertainty is larger than bias from ignoring the relation. In this paper, we propose a novel bagging predictor designed for such weak predictor variables. The predictor is based on a test for finitesample predictive ability. Our predictor shrinks the OLS estimate not to zero, but towards the null of the test which equates squared bias with estimation variance. We derive the asymptotic distribution and show that the predictor can substantially lower the MSE compared to standard t-test bagging. An asymptotic shrinkage representation for the predictor is provided that simplifies computation of the estimator. Monte Carlo simulations show that the predictor works well in small samples. In the empirical application, we find that the new predictor works well for inflation forecasts.
OriginalsprogEngelsk
UdgivelsesstedAarhus
UdgiverInstitut for Økonomi, Aarhus Universitet
Antal sider36
StatusUdgivet - 10 jan. 2014
SerietitelCREATES Research Papers
Nummer2014-01

    Forskningsområder

  • Inflation forecasting, bootstrap aggregation, estimation uncertainty, weak predictors

Se relationer på Aarhus Universitet Citationsformater

Download-statistik

Ingen data tilgængelig

ID: 68553823