Predicting the Number of Reported Pulmonary Tuberculosis in Guiyang, China, Based on Time Series Analysis Techniques

Table 8

Evaluation of fitting and prediction effect of Holt-Winters (additive and multiplicative) models.

Models	Parameter			Training set			Test set
	α	β	γ	MAPE (%)	RMSE	MAE	MAPE (%)	RMSE	MAE
Holt-Winters (additive)	0.220	0.000	0.480	11.930	42.732	34.438	8.101	28.689	21.003
Holt-Winters (multiplicative)	0.073	0.000	0.396	12.177	43.649	35.323	10.726	29.348	26.041