The conventional dividend–price ratio is highly persistent, and the literature reports mixed evidence on its role in predicting stock returns. We argue that the decreasing number of firms with a traditional dividend-payout policy is responsible for these results, and develop a model in which the long-run relationship between the dividends and stock price is time varying. An adjusted dividend–price ratio that accounts for the time-varying long-run relationship is considerably less persistent. Furthermore, the predictive regression model that employs the adjusted dividend–price ratio as a regressor outperforms the random-walk model. These results are robust with respect to the firm size.