Comparative study of arima model and GM(1,1)model on the prediction of hepatitis C incidence
Objective This study aims to explore and compare the predictive performance in practical application of the ARIMA model and the GM(1,1)model on the incidence rate of hepatitis C in Jin chang city from 2013 to 2022.Methods The data on hepatitis C incidence among residents in Jinchang city of Gansu province from 2012 to 2022 were collected from the Subsystem of Infectious Disease Surveillance in the China Disease Prevention and Control Information System.The ARIMA model and GM(1,1)model were established by using SPSS 25.0 software and Excel 2016 for prediction.The predictive performance of the models was evaluated by comparing the Mean Square Error(MSE),Root Mean Square Error(RMSE),Mean Absolute Error(MAE),and Mean Absolute Percentage Error(MAPE),α=0.05.Results The fitted models indicated that the optimal ARIMA model was ARIMA(3,1,1),and its prediction for the hepatitis C incidence rate in 2023 was 12.59/105.On the other hand,the GM(1,1)model predicted the incidence rate to be 14.78/105 in 2023.The evaluation metrics of the ARIMA(3,1,1)model and the GM(1,1)model were as follows:MSE=0.672 and 16.355,RMSE=0.809 and 4.044,MAE=0.647 and 3.656,and MAPE=10.913％and 14.911％,respectively.Conclusions The ARIMA(3,1,1)model shows better fitting performance compared to the GM(1,1)model.The ARIMA model demonstrated a significant advantage in predicting the incidence rate of hepatitis C in Jinchang city.It provides a more accurate approach for handling this type of time series data and can serve as a scientific reference to guide the development of corresponding prevention and control strategies by disease control departments.
万方数据
维普
