Space-Time Clustering

About: Space-Time Clustering is a research topic. Over the lifetime, 109 publications have been published within this topic receiving 13414 citations.

The Detection of Disease Clustering and a Generalized Regression Approach

Abstract: The problem of identifying subtle time-space clustering of disease, as may be occurring in leukemia, is described and reviewed. Published approaches, generally associated with studies of leukemia, not dependent on knowledge of the underlying population for their validity, are directed towards identifying clustering by establishing a relationship between the temporal and the spatial separations for the n ( n - 1)/2 possible pairs which can be formed from the n observed cases of disease. Here it is proposed that statistical power can be improved by applying a reciprocal transform to these separations. While a permutational approach can give valid probability levels for any observed association, for reasons of practicability, it is suggested that the observed association be tested relative to its permutational variance. Formulas and computational procedures for doing so are given. While the distance measures between points represent symmetric relationships subject to mathematical and geometric regularities, the variance formula developed is appropriate for arbitrary relationships. Simplified procedures are given for the case of symmetric and skew-symmetric relationships. The general procedure is indicated as being potentially useful in other situations as, for example, the study of interpersonal relationships. Viewing the procedure as a regression approach, the possibility for extending it to nonlinear and multivariate situations is suggested. Other aspects of the problem and of the procedure developed are discussed. Similarly, pure temporal clustering can be identified by a study of incidence rates in periods of widespread epidemics. In point of fact, many epidemics of communicable diseases are somewhat local in nature and so these do actually constitute temporal-spatial clusters. For leukemia and similar diseases in which cases seem to arise substantially at random rather than as clear-cut epidemics, it is necessary to devise sensitive and efficient procedures for detecting any nonrandom component of disease occurrence. Various ingenious procedures which statisticians have developed for the detection of disease clustering are reviewed here. These procedures can be generalized so as to increase their statistical validity and efficiency. The technic to be given below for imparting statistical validity to the procedures already in vogue can be viewed as a generalized form of regression with possible useful application to problems arising in quite different contexts.

Nonparametric intensity bounds for the delineation of spatial clusters

Abstract: Background There is considerable uncertainty in the disease rate estimation for aggregated area maps, especially for small population areas. As a consequence the delineation of local clustering is subject to substantial variation. Consider the most likely disease cluster produced by any given method, like SaTScan, for the detection and inference of spatial clusters in a map divided into areas; if this cluster is found to be statistically significant, what could be said of the external areas adjacent to the cluster? Do we have enough information to exclude them from a health program of prevention? Do all the areas inside the cluster have the same importance from a practitioner perspective?

Spatial Clustering of Amyotrophic Lateral Sclerosis in Finland at Place of Birth and Place of Death

Abstract: Previous evidence for spatial clustering of amyotrophic lateral sclerosis is inconclusive. Studies that have identified apparent clusters have often been based on a small number of cases, which means the results may have occurred by chance processes. Also, most studies have used the geographic location at the time of death as the basis for cluster detection, rather than exploring clusters at other points in the life cycle. In this study, the authors examine 1,000 cases of amyotrophic lateral sclerosis distributed throughout Finland who died between June 1985 and December 1995. Using a spatial-scan statistic, the authors examine whether there are significant clusters of the disease at both time of birth and time of death. Two significant, neighboring clusters were identified in southeast and south-central Finland at the time of death. A single significant cluster was identified in southeast Finland at the time of birth, closely matching one of the clusters identified at the time of death. These results are based on a large sample of cases, and they provide convincing evidence of spatial clustering of this condition. The results demonstrate also that, if the cluster analysis is conducted at different stages of the cases' life cycle, different conclusions about where potential risk factors may exist might result.

Clustering of Attempted Suicide: New Zealand National Data

Abstract: BACKGROUND: The extent to which clusters of attempted suicides occur is a significant problem that is complementary to the current available research on the clustering of completed suicide. However, little systematic research on clusters of attempted suicides exists. The present study examines the extent and nature of clustering of suicide attempts. METHOD: The occurrence of clustering of attempted suicide was examined in nationwide data for all New Zealand hospitals, obtained from the New Zealand Health Statistics Services for the years 1988-1990. The Scan statistic and Knox procedure were employed for testing the significance of clusters in time and time-space, respectively. RESULTS: The analyses indicated that significant time clustering occurred in younger age groups, specifically among 15-19 and 20-24 year olds. The results could not be accounted for by seasonal variations in admissions. Age specificity of time-space clusters emerged, exhibiting a similar pattern to that reported for completed suicides in the US. CONCLUSIONS: The results suggest a similar underlying mechanism for the clustering of parasuicide and completed suicides and provide support for the existence of contagion of suicidal behaviour. The implications for prevention are discussed. Language: en

Space-time clustering and correlations of major earthquakes.

Abstract: Earthquake occurrence in nature is thought to result from correlated elastic stresses, leading to clustering in space and time. We show that the occurrence of major earthquakes in California correlates with time intervals when fluctuations in small earthquakes are suppressed relative to the long term average. We estimate a probability of less than 1% that this coincidence is due to random clustering.