Abstract

Dengue Hemorrhagic Fever (DHF) is an endemic disease with potential to cause outbreaks. It progresses and often proves fatal, with a high mortality rate frequently attributed to delayed treatment. According to data from the West Nusa Tenggara (NTB) Provincial Health Office, the incidence of DHF in the region has shown a consistent upward trend year over year, necessitating increased vigilance and preventative measures. This study aims to develop an accurate forecasting model to predict the number of DHF cases. The resulting model is intended to serve as tool for the community and policymakers to anticipate the spread of the disease, particularly on Lombok Island. The analytical method employed is the Space-Time Autoregressive (STAR) model, a time-series technique that incorporates interdependencies across both location (space) and time. The data analyzed consists of monthly DHF case counts on Lombok Island from January 2018 to December 2-22. The research results indicate that the best-perfoming model is STAR (3, 1). The forecasting accuracy of this optimal model, measured by the Mean Absolute Scaled Error (MASE), for Central Lombok and North Lombok Regencies was 0.87 and 0.59, respectively. These MASE values, being less than 1, indicate that the forecasting performance of the STAR model is superior to that of a simple naïve baseline model.

Concepts :

Access to Document

Citations by Year