SARFIMA model prediction for infectious diseases: application to hemorrhagic fever with renal syndrome and comparing with SARIMA

Chang Qi,Yuchen Zhu,Lili Liu,Zhiqiang Wang,Dandan Zhang,Xiujun Li,Chunyu Li

doi:10.1186/s12874-020-01130-8

Abstract

BackgroundThe early warning model of infectious diseases plays a key role in prevention and control. This study aims to using seasonal autoregressive fractionally integrated moving average (SARFIMA) model to predict the incidence of hemorrhagic fever with renal syndrome (HFRS) and comparing with seasonal autoregressive integrated moving average (SARIMA) model to evaluate its prediction effect.MethodsData on notified HFRS cases in Weifang city, Shandong Province were collected from the official website and Shandong Center for Disease Control and Prevention between January 1, 2005 and December 31, 2018. The SARFIMA model considering both the short memory and long memory was performed to fit and predict the HFRS series. Besides, we compared accuracy of fit and prediction between SARFIMA and SARIMA which was used widely in infectious diseases.ResultsModel assessments indicated that the SARFIMA model has better goodness of fit (SARFIMA (1, 0.11, 2)(1, 0, 1)12: Akaike information criterion (AIC):-631.31; SARIMA (1, 0, 2)(1, 1, 1)12: AIC: − 227.32) and better predictive ability than the SARIMA model (SARFIMA: root mean square error (RMSE):0.058; SARIMA: RMSE: 0.090).ConclusionsThe SARFIMA model produces superior forecast performance than the SARIMA model for HFRS. Hence, the SARFIMA model may help to improve the forecast of monthly HFRS incidence based on a long-range dataset.

Highlights

The early warning model of infectious diseases plays a key role in prevention and control
seasonal autoregressive fractionally integrated moving average (SARFIMA) model allows for series to be fractionally integrated, generalizing the integer order of integration of the seasonal autoregressive integrated moving average (SARIMA) model to allow the d parameter to take on fractional values [21]
SARIMA model The augmented Dickey-Fuller (ADF) test indicates that the original series was stationary (Dickey-Fuller = − 3.95, P = 0.01), do not need for trend difference

Summary

Introduction

The early warning model of infectious diseases plays a key role in prevention and control. Time series analysis and modeling is widely used for studying temporal changes in the incidence of infectious diseases to forecast future trends [2, 5, 6]. Seasonal autoregressive integrated moving average (SARIMA) model has been used to fit and predict epidemics of many. The data preparation and model operation for SARIMA model are relatively simple and easy to perform [12], and the prediction results are accurate. Compared to the SARIMA which is an integer order model, the seasonal autoregressive fractionally integrated moving average (SARFIMA) model considering both the short memory and long memory may be more accurate when modeling the infectious diseases data possessing the long memory property [13, 14]. The SARFIMA is as simple and easy as the SARIMA to perform in R software

Objectives

Methods

Results

Discussion

Conclusion