Local multiplicity adjustments for spatial cluster detection

The spatial scan statistic is a widely applied tool for cluster detection. The spatial scan statistic evaluates the significance of a series of potential circular clusters using Monte Carlo simulation to account for the multiplicity of comparisons. In most settings, the extent of the multiplicity problem varies across the study region. For example, urban areas typically have many overlapping clusters, while rural areas have few. The spatial scan statistic does not account for these local variations in the multiplicity problem. We propose two new spatially-varying multiplicity adjustments for spatial cluster detection, one based on a nested Bonferroni adjustment and one based on local averaging. Geographic variations in power for the spatial scan statistic and the two new statistics are explored through simulation studies, and the methods are applied to both the well-known New York leukemia data and data from a case–control study of breast cancer in Wisconsin.     

A spatial zero-inflated poisson regression model for oak regeneration

Ecological counts data are often characterized by an excess of zeros and spatial dependence. Excess zeros can occur in regions outside the range of the distribution of a given species. A zero-inflated Poisson regression model is developed, under which the species range is determined by a spatial probit model, including physical variables as covariates. Within that range, species counts are independently drawn from a Poisson distribution whose mean depends on biotic variables. Bayesian inference for this model is illustrated using data on oak seedling counts. Received: May 2004 / Revised: December 2004     

Internal cohesion and geometric shape of spatial clusters

The geographic delineation of irregularly shaped spatial clusters is an ill defined problem. Whenever the spatial scan statistic is used, some kind of penalty correction needs to be used to avoid clusters’ excessive irregularity and consequent reduction of power of detection. Geometric compactness and non-connectivity regularity functions have been recently proposed as corrections. We present a novel internal cohesion regularity function based on the graph topology to penalize the presence of weak links in candidate clusters. Weak links are defined as relatively unpopulated regions within a cluster, such that their removal disconnects it. By applying this weak link cohesion function, the most geographically meaningful clusters are sifted through the immense set of possible irregularly shaped candidate cluster solutions. A multi-objective genetic algorithm (MGA) has been proposed recently to compute the Pareto-sets of clusters solutions, employing Kulldorff’s spatial scan statistic and the geometric correction as objective functions. We propose novel MGAs to maximize the spatial scan, the cohesion function and the geometric function, or combinations of these functions. Numerical tests show that our proposed MGAs has high power to detect elongated clusters, and present good sensitivity and positive predictive value. The statistical significance of the clusters in the Pareto-set are estimated through Monte Carlo simulations. Our method distinguishes clearly those geographically inadequate clusters which are worse from both geometric and internal cohesion viewpoints. Besides, a certain degree of irregularity of shape is allowed provided that it does not impact internal cohesion. Our method has better power of detection for clusters satisfying those requirements. We propose a more robust definition of spatial cluster using these concepts.     

Upper level set scan statistic for detecting arbitrarily shaped hotspots

A declared need is around for geoinformatic surveillance statistical science and software infrastructure for spatial and spatiotemporal hotspot detection. Hotspot means something unusual, anomaly, aberration, outbreak, elevated cluster, critical resource area, etc. The declared need may be for monitoring, etiology, management, or early warning. The responsible factors may be natural, accidental, or intentional. This proof-of-concept paper suggests methods and tools for hotspot detection across geographic regions and across networks. The investigation proposes development of statistical methods and tools that have immediate potential for use in critical societal areas, such as public health and disease surveillance, ecosystem health, water resources and water services, transportation networks, persistent poverty typologies and trajectories, environmental justice, biosurveillance and biosecurity, among others. We introduce, for multidisciplinary use, an innovation of the health-area-popular circle-based spatial and spatiotemporal scan statistic. Our innovation employs the notion of an upper level set, and is accordingly called the upper level set scan statistic, pointing to a sophisticated analytical and computational system as the next generation of the present day popular SaTScan. Success of surveillance rests on potential elevated cluster detection capability. But the clusters can be of any shape, and cannot be captured only by circles. This is likely to give more of false alarms and more of false sense of security. What we need is capability to detect arbitrarily shaped clusters. The proposed upper level set scan statistic innovation is expected to fill this need     

Residential radon concentration in the Abruzzo region (Italy): a different perspective for identifying radon prone areas

Indoor radon is an important risk factor for human health. Indeed radon inhalation is considered the second cause of lung cancer after smoking. During the last decades, in many countries huge efforts have been made in order to measuring, mapping and predicting radon levels in dwellings. Various researches have been devoted to identify those areas within the country where high radon concentrations are more likely to be found. Data collected through indoor radon surveys have been analysed adopting various statistical approaches, among which hierarchical Bayesian models and geostatistical tools are worth noting. The essential goal of this paper regards the identification of high radon concentration areas (the so-called radon prone areas) in the Abruzzo Region (Italy). In order to accurately pinpoint zones deserving attention for mitigation purpose, we adopt spatial cluster detection techniques, traditionally employed in epidemiology. As a first step, we assume that indoor radon measurements do not arise from a continuous spatial process; thus the geographic locations of dwellings where the radon measurements have been taken can be viewed as a realization of a spatial point process. Following this perspective, we adopt and compare recent cluster detection techniques: the simulated annealing scan statistic, the case event approach based on distance regression on the selection order and the elliptic spatial scan statistic. The analysis includes data collected during surveys carried out by the Regional Agency for the Environment Protection of Abruzzo (ARTA) in 1,861 random sampled dwellings across 277 municipalities of the Abruzzo region. The radon prone areas detected by the selected approaches are provided along with the summary statistics of the methods. Finally, the methodologies considered in this paper are tested on simulated data in order to evaluate their power and the precision of cluster location detection.     

Testing spatial cluster occurrence in maps equipped with environmentally defined structures

We propose a novel tool for testing hypotheses concerning the adequacy of environmentally defined factors for local clustering of diseases, through the comparative evaluation of the significance of the most likely clusters detected under maps whose neighborhood structures were modified according to those factors. A multi-objective genetic algorithm scan statistic is employed for finding spatial clusters in a map divided in a finite number of regions, whose adjacency is defined by a graph structure. This cluster finder maximizes two objectives, the spatial scan statistic and the regularity of cluster shape. Instead of specifying locations for the possible clusters a priori, as is currently done for cluster finders based on focused algorithms, we alter the usual adjacency induced by the common geographical boundary between regions. In our approach, the connectivity between regions is reinforced or weakened, according to certain environmental features of interest associated with the map. We build various plausible scenarios, each time modifying the adjacency structure on specific geographic areas in the map, and run the multi-objective genetic algorithm for selecting the best cluster solutions for each one of the selected scenarios. The statistical significances of the most likely clusters are estimated through Monte Carlo simulations. The clusters with the lowest estimated p-values, along with their corresponding maps of enhanced environmental features, are displayed for comparative analysis. Therefore the probability of cluster detection is increased or decreased, according to changes made in the adjacency graph structure, related to the selection of environmental features. The eventual identification of the specific environmental conditions which induce the most significant clusters enables the practitioner to accept or reject different hypotheses concerning the relevance of geographical factors. Numerical simulation studies and an application for malaria clusters in Brazil are presented.     

Zero-inflated models with application to spatial count data

Count data arises in many contexts. Here our concern is with spatial count data which exhibit an excessive number of zeros. Using the class of zero-inflated count models provides a flexible way to address this problem. Available covariate information suggests formulation of such modeling within a regression framework. We employ zero-inflated Poisson regression models. Spatial association is introduced through suitable random effects yielding a hierarchical model. We propose fitting this model within a Bayesian framework considering issues of posterior propriety, informative prior specification and well-behaved simulation based model fitting. Finally, we illustrate the model fitting with a data set involving counts of isopod nest burrows for 1649 pixels over a portion of the Negev desert in Israel.     

Space-time Bayesian small area disease risk models: development and evaluation with a focus on cluster detection

This paper extends the spatial local-likelihood model and the spatial mixture model to the space-time (ST) domain. For comparison, a standard random effect space-time (SREST) model is examined to allow evaluation of each model’s ability in relation to cluster detection. To pursue this evaluation, we use the ST counterparts of spatial cluster detection diagnostics. The proposed criteria are based on posterior estimates (e.g., misclassification rate) and some are based on post-hoc analysis of posterior samples (e.g., exceedance probability). In addition, we examine more conventional model fit criteria including mean square error (MSE). We illustrate the methodology with a real ST dataset, Georgia throat cancer mortality data for the years 1994–2005, and a simulated dataset where different levels and shapes of clusters are embedded. Overall, it is found that conventional SREST models fair well in ST cluster detection and in goodness-of-fit, while for extreme risk detection the local likelihood ST model does best.     

Detection and delineation of critical areas using echelons and spatial scan statistics with synoptic cellular data

Geographical surveillance for hotspot detection and delineation has become an important area of investigation both in geospatial ecosystem health and in geospatial public health. In order to find critical areas based on synoptic cellular data, geospatial ecosystem health investigations apply recently discovered echelon tools. In order to find elevated rate areas based on synoptic cellular data, geospatial public health investigations apply recently discovered spatial scan statistic tools. The purpose of this paper is to conceptualize a joint role for these together in the spirit of a cross-disciplinary cross-fertilization to accomplish more effective and efficient geographical surveillance for hotspot detection and delineation, and early warning system.     

Estimation of the mean in line intercept sampling

Ratio estimation of the parametric mean for a characteristic measured on plants sampled by a line intercept method is presented and evaluated via simulation using different plant dispersion patterns (Poisson, regular cluster, and Poisson cluster), plant width variances, and numbers of lines. The results indicate that on average the estimates are close to the parametric mean under all three dispersion patterns. Given a fixed number of lines, variability of the estimates is similar across dispersion patterns with variability under the Poisson pattern slightly smaller than varia-bility under the cluster patterns. No variance estimates were negative under the Poisson pattern, but some estimates were negative under the cluster patterns for smaller numbers of lines. Variance estimates become closer to zero similarly for all spatial patterns as the number of lines increases. Ratio estimation of the parametric mean in line intercept sampling works better, from the viewpoint of approximate unbiasedness and variability of estimates, under the Poisson pattern with larger numbers of lines than other combinations of spatial patterns, plant width variances and numbers of lines.     

Site-selection bias and apparent population declines in long-term studies

Detecting population declines is a critical task for conservation biology. Logistical difficulties and the spatiotemporal variability of populations make estimation of population declines difficult. For statistical reasons, estimates of population decline may be biased when study sites are chosen based on abundance of the focal species. In this situation, apparent population declines are likely to be detected even if there is no decline. This site-selection bias is mentioned in the literature but is not well known. We used simulations and real population data to examine the effects of site-selection biases on inferences about population trends. We used a left-censoring method to detect population-size patterns consistent with site-selection bias. The site-selection bias is an important consideration for conservation biologists, and we offer suggestions for minimizing or mitigating it in study design and analysis. Article impact statement: Estimates of population declines are biased if studies begin in large populations, and time-series data show a signature of such an effect.     

Spatial and space-time scan statistics to detect low rate clusters of sex ratio

Whether general environmental exposures to endocrine disrupting chemicals (including pesticides and dioxin) might induce decreased sex ratios (male/female ratio at birth) is discussed. To address this issue, the authors looked for a space-time clustering test which could detect local areas of significantly low risk, assuming a Bernoulli distribution. As a matter of fact, if the endocrine disruptor hypothesis holds true, and if the sex ratio is a sentinel health event indicative of new reproductive hazards ascribed to environmental factors, then in a given region, either a cluster of low male/female ratio among newborn babies would be expected in the vicinity of polluting municipal solid waste incinerators (MSWIs) (supporting the dioxin hypothesis), or local clusters would be expected in some rural areas where large amounts of pesticides are sprayed. Among cluster detection tests, the spatial scan statistic has been widely used in various applications to scan for areas with high rates, and rarely (if ever) with low rates. Therefore, the goal of this paper was to check the properties of the scan statistics under a given scenario (Bernoulli distribution, search for clusters with low rates) and to assess its added value in addressing the sex ratio issue. This study took place in the Franche-Comté region (France), mainly rural, comprising three main MSWIs, among which only one had high dioxin emissions level in the past. The study population consisted of 192,490 boys and 182,588 girls born during the 1975–1999 period. On the whole, the authors conclude that: (i) spatial and space-time scan statistics provide attractive features to address the sex ratio issue; (ii) sex ratio is not markedly affected across space and does not provide a reliable screening measure for detecting reproductive hazards ascribed to environmental factors.     

Accounting for rate instability and spatial patterns in the boundary analysis of cancer mortality maps

Boundary analysis of cancer maps may highlight areas where causative exposures change through geographic space, the presence of local populations with distinct cancer incidences, or the impact of different cancer control methods. Too often, such analysis ignores the spatial pattern of incidence or mortality rates and overlooks the fact that rates computed from sparsely populated geographic entities can be very unreliable. This paper proposes a new methodology that accounts for the uncertainty and spatial correlation of rate data in the detection of significant edges between adjacent entities or polygons. Poisson kriging is first used to estimate the risk value and the associated standard error within each polygon, accounting for the population size and the risk semivariogram computed from raw rates. The boundary statistic is then defined as half the absolute difference between kriged risks. Its reference distribution, under the null hypothesis of no boundary, is derived through the generation of multiple realizations of the spatial distribution of cancer risk values. This paper presents three types of neutral models generated using methods of increasing complexity: the common random shuffle of estimated risk values, a spatial re-ordering of these risks, or p-field simulation that accounts for the population size within each polygon. The approach is illustrated using age-adjusted pancreatic cancer mortality rates for white females in 295 US counties of the Northeast (1970–1994). Simulation studies demonstrate that Poisson kriging yields more accurate estimates of the cancer risk and how its value changes between polygons (i.e., boundary statistic), relatively to the use of raw rates or local empirical Bayes smoother. When used in conjunction with spatial neutral models generated by p-field simulation, the boundary analysis based on Poisson kriging estimates minimizes the proportion of type I errors (i.e., edges wrongly declared significant) while the frequency of these errors is predicted well by the p-value of the statistical test.

Inference about the ratio of means from Negative Binomial paired count data

We derive some statistical properties of the distribution of two Negative Binomial random variables conditional on their total. This type of model can be appropriate for paired count data with Poisson over-dispersion such that the variance is a quadratic function of the mean. This statistical model is appropriate in many ecological applications including comparative fishing studies of two vessels and or gears. The parameter of interest is the ratio of pair means. We show that the conditional means and variances are different from the more commonly used Binomial model with variance adjusted for over-dispersion, or the Beta-Binomial model. The conditional Negative Binomial model is complicated because it does not eliminate nuisance parameters like in the Poisson case. Maximum likelihood estimation with the unconditional Negative Binomial model can result in biased estimates of the over-dispersion parameter and poor confidence intervals for the ratio of means when there are many nuisance parameters. We propose three approaches to deal with nuisance parameters in the conditional Negative Binomial model. We also study a random effects Binomial model for this type of data, and we develop an adjustment to the full-sample Negative Binomial profile likelihood to reduce the bias caused by nuisance parameters. We use simulations with these methods to examine bias, precision, and accuracy of estimators and confidence intervals. We conclude that the maximum likelihood method based on the full-sample Negative Binomial adjusted profile likelihood produces the best statistical inferences for the ratio of means when paired counts have Negative Binomial distributions. However, when there is uncertainty about the type of Poisson over-dispersion then a Binomial random effects model is a good choice.     

PULSE,progressive upper level set scan statistic for geospatial hotspot detection

This paper presents a scan statistic, progressive upper level set (PULSE) scan statistic, for geospatial hotspot detection and its software implementation. Like ULS, the PULSE scan statistic is based on the arbitrarily shaped scan window and can be adapted for a network setting. PULSE is a refinement of the upper level set (ULS) scan statistic. Like some other likelihood based scanning devices, the ULS scan statistic identifies maximum likelihood estimate (MLE) zones that tend to be ‘stringy’ and sprawling. Its search path increases possibility of inclusion of extraneous cells in its MLE zones and, to a smaller extent, of exclusion of cells that belong to a true hotspot from its MLE zone. The PULSE scan statistic achieves improvement over the ULS scan statistic in two ways. First, it begins its search for a most likely zone with a large population of candidate zones obtained by modifying the ULS tree structure and continues its search using a genetic algorithm. Secondly, to reduce chances of generating an MLE that is excessively stringy and that includes extraneous cells in the MLE zone, PULSE uses cardinality and compactness of zones along with their likelihoods as the fitness function in the genetic algorithm and uses several pertinent criteria including evenness of intra-zone cellular response ratios to determine the MLE zone. To reduce computation, Gumbel distribution of extreme values is used to determine the p-value of the MLE zone. Better results come at the cost of increased processing time. An evaluative performance study is presented.     

Space-time stick-breaking processes for small area disease cluster estimation

We propose a space-time stick-breaking process for the disease cluster estimation. The dependencies for spatial and temporal effects are introduced by using space-time covariate dependent kernel stick-breaking processes. We compared this model with the space-time standard random effect model by checking each model’s ability in terms of cluster detection of various shapes and sizes. This comparison was made for simulated data where the true risks were known. For the simulated data, we have observed that space-time stick-breaking process performs better in detecting medium- and high-risk clusters. For the real data, county specific low birth weight incidences for the state of South Carolina for the years 1997–2007, we have illustrated how the proposed model can be used to find grouping of counties of higher incidence rate.     

Infant mortality and social environment in Georgia: an application of hotspot detection and prioritization

Recent years have witnessed the growth of new information technologies and their applications to various disciplines. The goal of this paper is to demonstrate how the two innovative methods, upper level set scan (ULS) hotspot detection and the multicriteria prioritization scheme, facilitate population health and break new ground in public health surveillance. It is believed that the social environment (i.e. social conditions and social capital) is one of the determinants of human health. Using infant health data and 10 additional indicators of social environment in the 159 counties of Georgia, ULS identified 52 counties that are in double jeopardy (high infant mortality and a high rate of low infant birth weight). The multicriteria ranking scheme suggested that there was no conspicuous spatial cluster of ranking orders, which improved the traditional decision making by visual geographic cluster. Both hotspot detection and ranking methods provided an empirical basis for re-allocating limited resources and several policy implications could be drawn from these analytic results.     

Markov Modulated Poisson Processes for Clustered Line Transect Data

We model the points of the detection along the transect line by a Markov modulated Poisson process (MMPP). The MMPP can accommodate the spatial cluster structure typical of many line transect surveys. The basic idea is that animal density switches between a low and a high level according to a latent Markov process. The MMPP is attractive from a mathematical point of view, as it provides an explicit expression for the likelihood function and other important quantities. We focus on estimating the level of overdispersion in the number of detected animals, as this is important for quantifying the precision of the line transect estimator of animal abundance. The approach is illustrated using both simulated data and data from a minke whale sighting survey conducted in the North Atlantic. Received: August 2004 / Revised: August 2005