Modeling and Prediction of the Volatility of the Freight Rate in the Roadway Freight Market of China

Table 5

In-sample forecast performance.

Route-specific TRV	Forecasting models
	SST-EGARCH		ARIMA		NN-EGARCH
	MAPE	MASE	MAPE	MASE	MAPE	MASE
R_CTG	0.781	0.985	0.898	1.109	0.775	1.006
R_CTK	1.205	0.918	1.125	0.886	1.015	0.837
R_CTQ	0.886	0.985	0.891	0.984	0.881	1.018
R_GTC	1.325	0.912	1.514	0.976	1.299	0.991
R_GTK	0.915	0.954	0.851	0.943	0.801	0.890
R_GTQ	0.531	0.899	0.622	1.016	0.512	0.895
R_KTC	0.489	0.936	0.458	0.895	0.451	0.884
R_KTG	0.587	0.998	0.612	1.036	0.553	0.968
R_KTQ	0.425	0.943	0.501	1.042	0.413	0.922
R_QTC	0.554	0.901	0.585	0.944	0.499	0.834
R_QTG	0.774	0.933	0.785	0.938	0.752	0.939
R_QTK	0.667	0.976	0.590	0.874	0.584	0.870

Bold values indicate best performance.