TY - JOUR
AU - Stambaugh, Robert F
TI - Predictive Regressions
JF - National Bureau of Economic Research Technical Working Paper Series
VL - No. 240
PY - 1999
Y2 - May 1999
DO - 10.3386/t0240
UR - http://www.nber.org/papers/t0240
L1 - http://www.nber.org/papers/t0240.pdf
N1 - Author contact info:
Robert F. Stambaugh
Finance Department
The Wharton School
University of Pennsylvania
Philadelphia, PA 19104-6367
Tel: 215/898-5734
Fax: 215/898-6200
E-Mail: stambaugh@wharton.upenn.edu
AB - When a rate of return is regressed on a lagged stochastic regressor, such as a dividend yield, the regression disturbance is correlated with the regressor's innovation. The OLS estimator's finite-sample properties, derived here, can depart substantially from the standard regression setting. Bayesian posterior distributions for the regression parameters are obtained under specifications that differ with respect to (i) prior beliefs about the autocorrelation of the regressor and (ii) whether the initial observation of the regressor is specified as fixed or stochastic. The posteriors differ across such specifications asset allocations in the presence of estimation risk exhibit sensitivity to those differences.
ER -