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

Table 1

Results of the fitting process for the models.

Fitting 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)OLS
Forecasting model	0.00141239	0.99897498	0.999285392	0.035314	3.885𝐸−06	1.97𝐸−03	8.936E−05
Gompertz with constant	0.00155774	0.99885993	0.99921341	0.039917	4.321𝐸−06	2.08𝐸−03	9.939𝐸−05
Gompertz	0.00168856	0.99878231	0.999173307	0.066631	4.665𝐸−06	2.16𝐸−03	1.073𝐸−04
Richards	0.00169607	0.99875511	0.999155808	0.055175	4.721𝐸−06	2.17𝐸−03	1.086𝐸−04
Box Cox	0.00189690	0.99856237	0.999070053	0.084240	5.523𝐸−06	2.35𝐸−03	1.270𝐸−04
FLOG	0.00192879	0.99851900	0.999058878	0.088561	5.705𝐸−06	2.39𝐸−03	1.312𝐸−04
Logistic with constant	0.00220999	0.99810868	0.99880778	0.091428	7.168𝐸−06	2.68𝐸−03	1.649𝐸−04
Bass	0.00220926	0.99810868	0.9988074	0.091236	7.169𝐸−06	2.68𝐸−03	1.649𝐸−04
Logistic	0.00296358	0.99696321	0.998073643	0.113653	1.227𝐸−05	3.50𝐸−03	2.823𝐸−04