Skip to main content
. 2013 Nov 6;8(11):e80969. doi: 10.1371/journal.pone.0080969

Table 3. Comparison of the fitting and prediction performance of the two models.

Prediction Fitting part
Validation part
error ARIMA GRNN-ARIMA ARIMA GRNN-ARIMA
MSE 0.6521 0.4467 0.1133 0.0958
MAE 0.5688 0.4966 0.2800 0.2555
MAPE 0.0677 0.0602 0.0361 0.0330

ARIMA=the autoregressive integrated moving average; GRNN=the generalized regression neural network; MSE=mean square error; MAE=mean absolute error; MAPE=mean absolute percentage error.