Usha Ananthakumar | Searcharxiv

arXiv2026

Count data modeling and forecasting of malaria incidence using generalized time series regression

Malaria remains a major public health concern in many urban regions of India, where timely prediction of malaria incidence is essential for effective surveillance and resource allocation. This study examines count data approaches for understanding and predicting malaria incidence in the Mumbai region. The analysis used monthly $\textit{Plasmodium vivax}$ surveillance data from the Health Management Information System (HMIS) collected between 2012 and 2019, together with meteorological variables. Initial Poisson regression models suggested strong associations between malaria incidence and environmental factors; however, diagnostic assessment revealed substantial overdispersion, indicating that the Poisson model did not adequately capture the data's variability. Negative binomial regression provided a better representation of the data and indicated that seasonal effects were more strongly associated with malaria incidence than individual climatic covariates. Residual analyses further identified significant serial dependence not captured by baseline regression models. To address this limitation, a Generalized Linear Autoregressive Moving Average (GLARMA) framework was implemented to model temporal correlation explicitly. Forecasts were generated using simulation-based methods and evaluated through rolling time series cross-validation. The GLARMA Negative binomial model consistently demonstrated superior predictive performance and greater predictive stability than competing regression and time series approaches. These findings highlight the importance of jointly accounting for overdispersion and serial dependence in malaria surveillance data and demonstrate the value of count time series models for supporting early warning systems in urban settings.

stat.AP↗

arXiv2024

Forecasting Malaria in Indian States: A Time Series Approach with R Shiny Integration

Malaria remains a significant public health challenge in many regions, necessitating robust predictive models to aid in its management and prevention. This study focuses on developing and evaluating time series models for forecasting malaria cases across eight Indian states: Jharkhand, Chhattisgarh, Maharashtra, Meghalaya, Mizoram, Odisha, Tripura, and Uttar Pradesh. We employed various modeling approaches, including polynomial regression with seasonal components, log-transformed polynomial regression, lagged difference models, and ARIMA models, to capture the temporal dynamics of malaria incidence. Comprehensive model fitting, residual analysis, and performance evaluation using metrics such as Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) indicated that the log-transformed polynomial regression model consistently outperformed other models in terms of accuracy and robustness across all states. Rolling forecast validation further confirmed the superior predictive capability of the log-transformed model over time. Additionally, an interactive R Shiny tool was developed to facilitate the use of these predictive models by researchers and public health officials. This tool allows users to input data, select modeling approaches, and visualize predictions and performance metrics, providing a practical tool for real-time malaria forecasting and decision-making support. Our findings highlight the critical role of appropriate modeling techniques in malaria prediction and offer valuable resources for enhancing malaria surveillance and response efforts.

stat.AP↗