This is a study on the current approaches and future challenges in spatial epidemiology. This is a concept that describes and analyzes geographic variations in disease. Several factors form the basis for spatial epidemiology. The factors considered in the application of spatial epidemiology include demographics, environments, behavior, socioeconomic factors, genetics, and infectious risk factors. Various advances in geographic information systems, availability of high-resolution, and the statistical methods for spatial epidemiology present new problems. They include the large random component that may predominate disease rates across small areas. Understanding of data quality is crucial. Data errors can result in large apparent disease excess in a locality.
Read more of the current approaches and future challenges of spatial epidemiology at
CURRENT APPROACHES AND TYPES OF SPATIAL EPIDEMIOLOGIC INQUIRY
The application of spatial epidemiology in small areas entails three primary areas; disease mapping, geographic correlation studies, and clustering, disease clusters, and surveillance. Disease maps typically show standardized mortality or morbidity ratios. One of the challenges in spatial epidemiology in this area is losing apparent patterns artifactually depending on the depiction of the mapped variable. Other associated problems involve the geographic scale or resolution. In geographic correlation studies, the aim is to examine geographic variations across population groups in exposure to environmental variables. Specialists may combine various statistical methods for spatial epidemiology to investigate disease clusters and disease incidence near a point source.
Read more of the types of spatial epidemiologic inquiry at
CURRENT STATISTICAL METHODS FOR SPATIAL EPIDEMIOLOGY
This section reviews the statistical methods for spatial epidemiology. Some of the techniques, such as spatial regression, incorporate spatial autocorrelation according to the definition of spatial neighbors. We can use common methods in the application of spatial epidemiology to incorporate spatially correlated error terms in the variance-covariance matrix Σσ. They include the Simultaneous Spatial Autoregressive (SAR), Conditional spatial Autoregressive models (CAR), and Spatial Moving Average models (SMA). Professionals develop various software to counter the challenges in spatial epidemiology. Typical amongst them is the free software GeoDa [75], which easily fits both spatial lag and error models. LeSage and Pace developed the comprehensive econometric toolbox in MATLAB, which has numerous functions for fitting spatial regression models.
Read more of the current statistical methods for spatial epidemiology at
Additional attachments
>> Download