Abstract The focus of this article is on the predictive role of the stock-bond yield gap—the difference between the stock market earnings (dividend) yield and the 10-year Treasury bond yield—also known as the “Fed model”. The results show that the yield gap forecasts positive excess market returns, both at short and long forecasting horizons, and for both value- and equal-weighted stock indexes, and it also outperforms competing predictors commonly used in the literature. These findings go in line with the predictions from a present-value decomposition. The absence of predictive power for dividend growth, dividend payout ratios, earnings growth, and future one-period interest rates, actually strengthens the return predictability associated with the yield gap at very long horizons. By performing an out-of-sample analysis, the results show that the yield gap has reasonable out-of-sample predictability for the equity premium when the comparison is made against a simple historical average, especially when one imposes a restriction of positive equity premia. Furthermore, the yield gap proxies generally show greater out-of-sample forecasting power than the alternative state variables. An investment strategy based on the forecasting ability of the yield gap produces significant gains in Sharpe ratios.