This paper examines the effects of uncertainty about the stock return predictability on optimal dynamic portfolio choice in a continuous time setting for a longhorizon investor. Uncertainty about the predictive relation affects the optimal portfolio choice through dynamic learning, and leads to a state‐dependent relation between the optimal portfolio choice and the investment horizon. There is substantial market timing in the optimal hedge demands, which is caused by stochastic covariance between stock return and dynamic learning. The opportunity cost of ignoring predictability or learning is found to be quite substantial.

The optimal portfolio strategy is developed for an investor who has detected an asset pricing anomaly but is not certain that the anomaly is genuine rather than merely apparent. The analysis takes account of the fact that the parameters of both the underlying asset pricing model and the anomalous returns are estimated rather than known. The value that an investor would place on the ability to invest to exploit the apparent anomaly is also derived and illustrative calculations are presented for the Fama and French SMB and HML portfolios, whose returns are anomalous relative to the CAPM.

The optimal portfolio strategy is developed for an investor who has detected an asset pricing anomaly but is not certain that the anomaly is genuine rather than merely apparent. The analysis takes account of the fact that the parameters of both the underlying asset pricing model and the anomalous returns are estimated rather than known. The value that an investor would place on the ability to invest to exploit the apparent anomaly is also derived and illustrative calculations are presented for the Fama and French SMB and HML portfolios, whose returns are anomalous relative to the CAPM.