Analysis and prediction of incidence trends of mumps in Hebei Province based on three kinds of models
Objective To compare the forecast effects of different prediction models on the incidence of mumps in Hebei Province,to explore the application values of the prediction models in forecasting infectious diseases,and to provide references for improving the future work efficiency as well as scientific prevention and control.Methods The number of mumps cases from January 2008 to December 2021 was collected,and the fitted models were developed using multiple linear regression,grey GM(1,1)and ARIMA.The number of mumps cases in each month of 2022 was predicted,and then the predicted data were compared with the actual values to verify the prediction effect.Results The prediction results of the three models were in a good range of modeling.The maximum absolute value of the relative error between the predicted and actual data was 64.19％,whereas the minimum value 1.13％,which was controlled within the 95％confidence interval.The accuracy was still good,and could be used to predict the data of other years.The average relative error values of the regression model,the GM(1,1)model and the ARIMA model were 23.22％,24.01％and 31.59％respectively.The multiple regression model showed better effect on predicting the results.Conclusion The three models based on three kinds of prediction methods,namely,multiple linear regression,grey GM(1,1)and ARIMA are well fitted with the trends of mumps incidence,which can be extrapolated to prediction of other infectious diseases.
万方数据
维普
