Analysis of Spatial Data with a Nested Correlation Structure

Abstract

Summary Spatial statistical analyses are often used to study the link between environmental factors and the incidence of diseases. In modelling spatial data, the existence of spatial correlation between observations must be considered. However, in many situations, the exact form of the spatial correlation is unknown. This paper studies environmental factors that might influence the incidence of malaria in Afghanistan. We assume that spatial correlation may be induced by multiple latent sources. Our method is based on a generalized estimating equation of the marginal mean of disease incidence, as a function of the geographical factors and the spatial correlation. Instead of using one set of generalized estimating equations, we embed a series of generalized estimating equations, each reflecting a particular source of spatial correlation, into a larger system of estimating equations. To estimate the spatial correlation parameters, we set up a supplementary set of estimating equations based on the correlation structures that are induced from the various sources. Simultaneous estimation of the mean and correlation parameters is performed by alternating between the two systems of equations.

Analysis of COVID-19 Cases' Spatial Dependence in US Counties Reveals Health Inequalities

“…Descriptive summaries of study characteristics were presented as mean, median and interquartile range. Often in spatial data, there is some degree of dependency among observations within a geographical space (28,29); therefore, we measured the bivariate spatial autocorrelation between county-level health factors and the number of confirmed COVID-19 cases using Moran's Index based on Queen's contiguity spatial-lag of order 1 (immediate neighbors) (30). Moran's I is the most common measure of global spatial autocorrelation which gives the overall distribution of departures from randomness.…”

Spatial modelling of contribution of individual level risk factors for mortality from Middle East respiratory syndrome coronavirus in the Arabian Peninsula

“…While the work of Rivers and colleagues was practically impeccable, their analysis adopted Poisson regression models using a robust variance estimator without accounting for area-specific geographical effects to capture extra variation in the model. Ignoring spatial pattern in infectious disease may be inadequate to explain the variation in the occurrence of the disease due to space as it has been found that most diseases are location related [ 41 , 42 ]. Similarly, Alraddadi et al, [ 14 ] considered only primary MERS-CoV cases reported in Saudi Arabia during March–November 2014 in their study.…”

The spatio-temporal epidemic dynamics of COVID-19 outbreak in Africa

“…There have been a number of applications of statistical models for prediction of infection rates and spread during the COVID-19 pandemic [9,10]. However, mapping of disease incidence to identify spatial clustering and patterns remains an important pathway to understanding disease epidemiology and is required for effective planning, prevention or containment action [11][12][13]. There are a few studies that attempt to map the pandemic in China [14] and in Iran [15].…”