Economic evaluation of commodity price forecasting models

Price forecasts are typically evaluated on the basis of statistical criteria, such as mean error, mean absolute error, or root mean squared error. An alternative approach for evaluating price forecasts is to analyze them using economic criteria. Four types of economic criteria are applied to five quarterly hog price forecasting models over the period 1976:I-1985:IV. In general, model evaluations under the different economic criteria are consistent with one another. However, the economic evaluations are not consistent with those found using traditional statistical evaluation.