In this paper, we investigate the long-run relationship between stock prices and GDP in Sweden. Using quarterly data from 1995 to 2015, our empirical analysis suggests that the two variables are cointegrated and, hence, that there exists a long-run equilibrium relationship between them. In light of this long-run relationship, we estimate a vector error correction model. The estimated model outperforms a simple, but highly relevant, alternative method in an out-of-sample forecast exercise. It also provides information as to whether Swedish stocks are correctly valued. Results indicate that stocks in Sweden might be overvalued at the end of the sample and forecasts from the model suggest that the disequilibrium will generate a modest development in the stock market over a number of quarters.