Predicting returns and dividend growth - the role of non-Gaussian innovations

In this paper we assess whether exible modelling of innovations impact the predictive performance of the dividend price ratio for returns and dividend growth. Using Bayesian vector autoregressions we allow for stochastic volatility, heavy tails and skewness in the innovations. Our results suggest that point forecasts are barely affected by these features, suggesting that workhorse models on predictability are sufficient. For density forecasts, however, we finnd that stochastic volatility substantially improves the forecasting performance.