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

Table 10

Evaluation of fitting and prediction effect of time series models.

Models	Training set			Test set
	MAPE (%)	RMSE	MAE	MAPE (%)	RMSE	MAE
ARIMA (1, 1, 1) (0, 1, 2)12	10.184	38.375	29.578	7.081	26.771	18.601
ARIMAX (1, 1, 1) (0, 1, 2)12 + AAP (lag 7)	10.164	37.570	28.511	6.901	20.724	17.306
Holt-Winters (additive)	11.930	42.732	34.438	8.101	28.689	21.003
Multivariable LSTM+RH (lag 6) + APP (lag 7)	10.105	34.615	28.961	12.758	35.167	28.562