Remarks on a ‘critique’ of the Bayesian Method of Moments

Error measures for the evaluation of forecasts are usually based on the size of the forecast errors. Common measures are, e.g. the mean squared error (MSE), the mean absolute deviation (MAD) or the mean absolute percentage error (MAPE). Alternative measures for the comparison of forecasts are turning points or hits-and-misses, where an indicator loss function is used to decide if a forecast is of high quality or not. Here, we discuss the latter to obtain reliable combined forecasts. We apply several combination techniques to a set of German macroeconomic data. Furthermore, we perform a small simulation study for the combination of two biased forecasts.