Cluster Detection Based on Spatial Associations and Iterated Residuals in Generalized Linear Mixed Models

• Published in: Biometrics Vol. 65; no. 2; pp. 353 - 360
• Main Authors: Zhang, Tonglin, Lin, Ge
• Format: Journal Article
• Language: English
• Published: Malden, USA Blackwell Publishing Inc 01-06-2009; Wiley-Blackwell Publishing; Blackwell Publishing Ltd
• Subjects: Algorithms; Biometric Methodology; Biometrics; Biometry - methods; Biostatistics; Cluster Analysis; Coefficients; Colorectal cancer; Computer Simulation; Data Interpretation, Statistical; Disease models; Ecological modeling; Epidemiologic Research Design; Frequentism; Generalized linear models; Linear Models; Local clusters; Mathematical models; Mixed effects; Moran's I statistic; Mortality; P values; Pattern Recognition, Automated; Pearson residuals; Proportional Hazards Models; Reproducibility of Results; Risk Assessment - methods; Sensitivity and Specificity; Spatial heterogeneity; Spatial models; Statistical methods; Statistics
• ISSN: 0006-341X; 1541-0420
• DOI: 10.1111/j.1541-0420.2008.01069.x

Spatial clustering is commonly modeled by a Bayesian method under the framework of generalized linear mixed effect models (GLMMs). Spatial clusters are commonly detected by a frequentist method through hypothesis testing. In this article, we provide a frequentist method for assessing spatial properties of GLMMs. We propose a strategy that detects spatial clusters through parameter estimates of spatial associations, and assesses spatial aspects of model improvement through iterated residuals. Simulations and a case study show that the proposed method is able to consistently and efficiently detect the locations and magnitudes of spatial clusters.