The paper introduces a Bayesian cross-entropy forecast (BCEF) procedure to assess the variance and skewness in density forecasting. The methodology decomposes the variance and skewness of the predictive distribution accounting for the shares of selected risk factors. The method assigns probability distributions to baseline-projections of an economic or social random variable-for example, gross domestic product growth, inflation, population growth, poverty headcount, among others-combining ex-post and ex-ante market information. The generated asymmetric density forecasts use information derived from surveys on expectations and implied statistics of predictive models. The BCEF procedure is applied to produce world GDP growth forecasts for three-year horizons using information spanning the period of October 2005-August 2015. The scores indicate that the BCEF density forecasts are more accurate and reliable than some naïve-symmetric and normal distributed confidence interval-predictions, illustrating the value-added of the introduced methodology.