Generalized Autoregressive Conditional Heteroskedastic Model to Examine Silver Price Volatility and Its Macroeconomic Determinant in Ethiopia Market

Table 6

Comparison of candidate models for the price volatility of silver using the forecasting accuracy measures.

Candidate model	Error distribution	Forecasting accuracy measure
		RMSE	MAE	MAPE
GARCH-M(1, 2)	GED	0.1181	0.0770	128.08
GARCH(2, 0)	GED	0.1157	0.0786	126.63
GARCH(3, 3)	GED	0.1142	0.0781	121.23
EGARCH(3, 2)	Normal	0.1122	0.0632	112.357
TGARCH(0, 1)	GED	0.115	0.077	118.99
TGARCH(3, 3)	GED	0.116	0.079	128.03

RMSE: root mean squared error; MAE: mean absolute error; MAPE: mean absolute percent error.