Disease mapping for spatially semi-continuous data by estimating equations with application to dengue control

Area of Science:

• Epidemiology
• Biostatistics
• Spatial Analysis

Background:

• Disease mapping identifies geographical patterns of health risks.
• Dengue fever causes seasonal epidemics, particularly in Taiwan.
• Analyzing zero-inflated spatial data presents statistical challenges.

Purpose of the Study:

• To develop a robust statistical model for disease mapping with zero-inflated, spatially correlated data.
• To address limitations of existing methods in handling complex disease data.
• To accurately estimate disease risks and identify high-risk geographical areas.

Main Methods:

• Development of estimating equations for a mixture regression model.
• Incorporation of spatial dependence and zero-inflation into the model.
• Establishment of asymptotic properties for the proposed estimates.

Main Results:

• The proposed mixture regression model effectively accommodates spatial dependence and zero inflation.
• The method overcomes computational burdens and missed associations of prior techniques.
• Simulation studies confirmed the performance of the mixture estimating equations.

Conclusions:

• The developed statistical approach enhances disease mapping for zero-inflated data.
• This method provides a valuable tool for studying disease propagation and risk.
• Application to a dengue dataset in Taiwan demonstrates practical utility.