Tests for directional space-time interaction in epidemiological data

Goodness-of-fit measures for individual-level models of infectious disease in a Bayesian framework

In simple models there are a variety of tried and tested ways to assess goodness-of-fit. However, in complex non-linear models, such as spatio-temporal individual-level models, less research has been done on how best to ascertain goodness-of-fit. Often such models are fitted within a Bayesian statistical framework, since such a framework is ideally placed to account for the many areas of data uncertainty. Within a Bayesian context, a major tool for assessing goodness-of-fit is the posterior predictive distribution. That is, a distribution for a test statistic is found through simulation from the posterior distribution and then compared with the observed test statistic for the data. Here, we examine different test statistics and ascertain how well they can detect model misspecification via a simulation study.

Spatial statistical methods in health

The study of the geographical distribution of disease incidence and its relationship to potential risk factors (referred to here as "geographical epidemiology") has provided, and continues to provide, rich ground for the application and development of statistical methods and models. In recent years increasingly powerful and versatile statistical tools have been developed in this application area. This paper discusses the general classes of problem in geographical epidemiology and reviews the key statistical methods now being employed in each of the application areas identified. The paper does not attempt to exhaustively cover all possible methods and models, but extensive references are provided to further details and to additional approaches. The overall aim is to provide a picture of the "current state of the art" in the use of spatial statistical methods in epidemiological and public health research. Following the review of methods, the main software environments which are available to implement such methods are discussed. The paper concludes with some brief general reflections on the epidemiological and public health implications of the use of spatial statistical methods in health and on associated benefits and problems.

[AIDS epidemic dynamics in the municipality of Rio de Janeiro, Brazil, 1988-1996: Spatial-temporal statistic modeling]

This study uses a spatial-temporal model to analyze the spatial spread of the AIDS epidemic (adult cases) in the municipality of Rio de Janeiro, Brazil, during three periods: 1988-1990, 1991-1993, and 1994-1996. City districts were used as the geographic units of analysis. A spatial analysis was also performed for pediatric AIDS cases due to vertical HIV transmission, according to period of birth, 1985-90 and 1991-96. For total adult AIDS cases, the initial period was characterized by a polygonal cluster located around the harbor area, which expanded from west to east. Among homosexual cases, in situ growth predominated, and a decrease in the intensity of the diffusion process was observed from the second to the final period. Among heterosexual cases, the epidemic displayed a relevant geographic spread, mainly from 1988-1990 to 1991-1993. Among female cases in the final time period, a cluster of high incidence rates was found towards the northwest, including very poor areas. Among pediatric cases in 1991-1996, a significant correlation was found between AIDS incidence rates and poverty levels in the respective municipal districts. The results suggest that a more complete understanding of AIDS spatial-temporal dynamics can make a major contribution to preventive measures.

[Studies on space-time disease clusters: concepts, techniques, and challenges]

Methods for the analysis of space-time clusters have been used frequently in epidemiology and public health in recent decades. However, they have generally been applied without an appropriate critique of their limits and usefulness. This article reviews some of the most important issues involved in improving the interpretability and utility of such methods in this context. We begin with a brief discussion about the epidemiological meaning of the concept of space-time clustering. We then describe five commonly used methods, including the procedures for their use. We also present a conceptual and statistical generalization of the techniques. Finally, we summarize some important issues for use of these methods in epidemiology and public health.