Stambaugh Correlations and Redundant Predictors

48 Pages Posted: 17 Mar 2010

See all articles by Donald Robertson

Donald Robertson

Cambridge University - Department of Economics

Stephen H. Wright

Birkbeck College, University of London

Date Written: March 15, 2010

Abstract

We consider inference in a widely used predictive model in empirical finance. "Stambaugh Bias" arises when innovations to the predictor variable are correlated with those in the predictive regression. We show that high values of the "Stambaugh Correlation" will arise naturally if the predictor is actually redundant, but simply proxies univariate predictability. For such predictors even bias-corrected conventional tests will be severely distorted. We propose tests that distinguish well between redundant predictors and the true (or "perfect") predictor. An application of our tests does not reject the null that a range of predictors of stock returns are redundant.

Keywords: predictive return regressions, Stambaugh bias, ARMA models, predictive systems

JEL Classification: C22, G12

Suggested Citation

Robertson, Donald and Wright, Stephen H., Stambaugh Correlations and Redundant Predictors (March 15, 2010). Available at SSRN: https://ssrn.com/abstract=1571423 or http://dx.doi.org/10.2139/ssrn.1571423

Donald Robertson

Cambridge University - Department of Economics ( email )

Sidgwick Avenue
Cambridge, CB3 9DE
United Kingdom
+44 1223 335275 (Phone)
+44 1223 335475 (Fax)

Stephen H. Wright (Contact Author)

Birkbeck College, University of London ( email )

Malet St
London, WC1 E7HX
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
74
Abstract Views
821
rank
392,120
PlumX Metrics