Evaluation of best model of H9 in chickens.

In-sample data are for the fitted model. Other methods are described in Figure 2. Note that MSPE emphasizes deviations from larger peaks. The in-sample data show poorer performance relative to the forecasts since the first 3 years of data contained several much larger peaks than the last year of data.Mean Squared Prediction Error (MSPE): sum(y-m)2/N; smaller values indicate better fits; y = observed data; m = mean of predicted data; N = number of points predicted.Normalized Mean Squared Prediction Error (NMSPE): sum((y-m)/s)2/N; smaller values indicate better fits; y = observed data; m = mean of predicted data; s = standard deviation of predicted data; N = number of points predicted.