Jackknifing Stock Return Predictions

We show that the general bias reducing technique of jackknifing can be successfully applied to stock return predictability regressions. Compared to standard OLS estimation, the jackknifing procedure delivers virtually unbiased estimates with mean squared errors that generally dominate those of the OLS estimates. The jackknifing method is very general, as well as simple to implement, and can be applied to models with multiple predictors and overlapping observations. Unlike most previous work on inference in predictive regressions, no specific assumptions regarding the data generating process for the predictors are required. A set of Monte Carlo experiments show that the method works well in finite samples and the empirical section finds that out-of-sample forecasts based on the jackknifed estimates tend to outperform those based on the plain OLS estimates. The improved forecast ability also translates into economically relevant welfare gains for an investor who uses the predictive regression, with jackknifed estimates, to time the market.

[1]  Rossen Valkanov.  Long-horizon regressions: theoretical results and applications , 2003 .

[2]  P. Phillips,et al.  Jackknifing Bond Option Prices , 2003 .

[3]  M. H. Quenouille.  NOTES ON BIAS IN ESTIMATION , 1956 .

[4]  W. Torous,et al.  On Predicting Stock Returns with Nearly Integrated Explanatory Variables , 2004 .

[5]  M. Shapiro,et al.  Do We Reject Too Often? Small Sample Properties of Tests of Rational Expectations Models , 1985 .

[6]  Allan Timmermann,et al.  Instability of Return Prediction Models , 2005 .

[7]  Clifford M. Hurvich,et al.  Predictive Regressions: A Reduced-Bias Estimation Method , 2002, Journal of Financial and Quantitative Analysis.

[8]  C. Nelson,et al.  Predictable Stock Returns: The Role of Small Sample Bias , 1993 .

[9]  John Y. Campbell,et al.  Why Long Horizons: A Study of Power Against Persistent Alternatives , 1993 .

[10]  J. Stock,et al.  Drawing Inferences from Statistics Based on Multi-Year Asset Returns , 1989 .

[11]  R. Stambaugh,et al.  Predictive Regressions , 1999 .

[12]  William N. Goetzmann,et al.  Testing the Predictive Power of Dividend Yields , 1993 .

[13]  Yong Bao.  THE APPROXIMATE MOMENTS OF THE LEAST SQUARES ESTIMATOR FOR THE STATIONARY AUTOREGRESSIVE MODEL UNDER A GENERAL ERROR DISTRIBUTION , 2007, Econometric Theory.

[14]  Andrew Ang,et al.  Stock Return Predictability: Is it There? , 2001 .

[15]  J. Kiviet,et al.  Improved Coefficient and Variance Estimation in Stable First-Order Dynamic Regression Models , 2003 .

[16]  I. Welch,et al.  A Comprehensive Look at the Empirical Performance of Equity Premium Prediction II , 2004, SSRN Electronic Journal.

[17]  J. Kiviet,et al.  Moment Approximation for Least-Squares Estimators in Dynamic Regression Models with a Unit Root , 2005 .

[18]  S. B. Thompson,et al.  Predicting Excess Stock Returns Out of Sample: Can Anything Beat the Historical Average? , 2008 .

[19]  Piotr Eliasz.  OPTIMAL MEDIAN UNBIASED ESTIMATION OF COEFFICIENTS ON HIGHLY PERSISTENT REGRESSORS , 2004 .

[20]  R. Shiller,et al.  Stock Prices, Earnings and Expected Dividends , 1988 .

[21]  J. Lewellen,et al.  Predicting Returns with Financial Ratios , 2002 .

[22]  Matthew Richardson,et al.  Tests of financial models in the presence of overlapping observations , 1991 .

[23]  Graham Elliott,et al.  Inference in Models with Nearly Integrated Regressors , 1995, Econometric Theory.

[24]  L. Hansen,et al.  Forward Exchange Rates as Optimal Predictors of Future Spot Rates: An Econometric Analysis , 1980, Journal of Political Economy.

[25]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .