K-step ahead prediction models for dengue occurrences

Abstract

The paper proposed prediction model to study dengue occurrence in Malaysia, focusing on a region of Petaling district, in the state of Selangor. A number of different linear regression models were compared using model orders of lag time, and best model is selected using Akaike Information Criterion (AIC) value. First, dengue estimation models were built for Petaling district using weather variables of mean temperature, relative humidity, cumulative rainfall, and dengue feedback data. The best estimation model is then used to build dengue prediction models, using the k-steps ahead prediction (with one and multiple-step ahead predictions). One-step ahead prediction model was found to capture well pattern of dengue incidences. This information is believed to help health authorities in providing a reminder alarm to the public through medias, on precautions specifically against mosquitoes bites, especially when dengue occurrences is expected to be high.