A New Empirical Model for Short-Term Forecasting of the Broadband Penetration: A Short Research in Greece

Table 4

Results of the forecasting process for the models.

Forecasting performance
Model	Mean Absolute Error (MAE)	R-Square	Correlation	Mean Absolute Percentage Error (MAPE)	Mean Squared Error (MSE)	Root Mean Squared Error (RMSE)	Sum of Squared Error (SSE)WLS
Forecasting Model	0.00150121	0.99877253	0.999202491	0.032060	4.719𝐸−06	2.17𝐸−03	0.049023031
Gompertz with constant	0.00158061	0.99876359	0.99920045	0.033855	4.346𝐸−06	2.08𝐸−03	0.058116463
Richards	0.00186277	0.99834027	0.998929485	0.040750	5.837𝐸−06	2.42𝐸−03	0.068116161
Gompertz	0.00160523	0.99874607	0.999194834	0.047587	4.759𝐸−06	2.18𝐸−03	0.099948481
Box Cox	0.00200287	0.99844018	0.998966248	0.060265	6.048𝐸−06	2.46𝐸−03	0.058156471
FLOG	0.00199725	0.99844119	0.998967742	0.062505	6.161𝐸−06	2.48𝐸−03	0.054860705
Bass	0.00231788	0.99800684	0.998677706	0.084474	8.561𝐸−06	2.93𝐸−03	0.056633745
Logistic with constant	0.00231846	0.99800583	0.998677	0.084541	8.569𝐸−06	2.93𝐸−03	0.056633711
Logistic	0.00323439	0.99696693	0.998468875	0.111882	1.385𝐸−05	3.72𝐸−03	0.274783412