UNCERTAINTY OF EXTREME FLOOD ESTIMATES INCORPRATING HISTORICAL DATA1

ABSTRACT: The ability to predict extreme floods is an important part of the planning process for any water project for which failure will be very costly. The length of a gage record available for use in estimating extreme flows is generally much shorter than the recurrence interval of the desired flows, resulting in estimates having a high degree of uncertainty. Maximum likelihood estimators of the parameters of the three parameter lognormal (3PLN) distribution, which make use of historical data, are presented. A Monte Carlo study of extreme flows estimated from samples drawn from three hypothetical 3PLN populations showed that inclusion of historical flows with the gage record reduced the bias and variance of extreme flow estimates. Asymptotic theory approximations of parameter variances and covariances calculated using the second and mixed partial derivatives of the log likelihood function agreed well with Monte Carlo results. First order approximations of the standard deviations of the extreme flow estimates did not agree with the Monte Carlo results. An alternative method for calculating those standard deviations, the “asymptotic simulation” method, is described. The standard deviations calculated by asymptotic simulation agree well with the Monte Carlo results.     

GROUND AND SURFACE WATER QUALITY IMPACTS OF NORTH CAROLINA SANITARY LANDFILLS1

ABSTRACT: Ground and surface water quality monitoring data from 71 municipal sanitary landfills in North Carolina were analyzed to determine the nature and extent of current contamination problems and identify any common characteristics associated with this contamination. A total of 322 surface and 411 ground water quality records were analyzed using the SAS data system. Almost all the landfill records included inorganic and heavy metal analyses while approximately half of the records also included organic analyses by CC/MS. Our analysis indicates that landfills are having measurable impacts on ground and surface water quality, but these impacts may not be as severe as is commonly assumed. Statistically significant increases were detected in the average concentrations in ground water and downstream surface water samples when compared to upstream surface water samples. The largest percentage increases were observed for zinc, turbidity, total organic carbon, conductivity, total dissolved solids, and lead. Violations of ground water quality standards for heavy metals and hazardous organic compounds were detected at 53 percent of the landfills where adequate data existed. The moat common heavy metal violations were for lead (18 percent), chromium (18 percent), zinc (6 percent), cadmium (6 percent), and arsenic (6 percent) (percentage of landfills violating shown in parenthesis). The organic compounds that appear to pose the greatest threat to ground water are the chlorinated solvents (8 percent), petroleum derived hydrocarbons (8 percent), and pesticides (5 percent). A comparison of monitoring data from sanitary landfills and secondary wastewater treatment plants suggests that the concentrations of heavy metal and organic pollutants discharged to surface waters from these two sources are similar.     

城市污水测算统计方法

当今城市生活污水统计以人口与供水量为依据测算 ,难以满足治理和管理工作需要。在城市污水处理场和污水在线监控系统建设快速发展条件下建立以排污口监测统计为基础的城市污水统计系统 ,能够较真实反映生活污水质量和分布 ,满足环境管理工作需要。     

Nonparametric Ranked-set Sampling Confidence Intervals for Quantiles of a Finite Population

Ranked-set sampling from a finite population is considered in this paper. Three sampling protocols are described, and procedures for constructing nonparametric confidence intervals for a population quantile are developed. Algorithms for computing coverage probabilities for these confidence intervals are presented, and the use of interpolated confidence intervals is recommended as a means to approximately achieve coverage probabilities that cannot be achieved exactly. A simulation study based on finite populations of sizes 20, 30, 40, and 50 shows that the three sampling protocols follow a strict ordering in terms of the average lengths of the confidence intervals they produce. This study also shows that all three ranked-set sampling protocols tend to produce confidence intervals shorter than those produced by simple random sampling, with the difference being substantial for two of the protocols. The interpolated confidence intervals are shown to achieve coverage probabilities quite close to their nominal levels. Rankings done according to a highly correlated concomitant variable are shown to reduce the level of the confidence intervals only minimally. An example to illustrate the construction of confidence intervals according to this methodology is provided.     

A set of associated statistical tests for spatial clustering

The purpose of this paper is to develop a set of associated statistical tests for spatial clustering. In particular, a set of three associated tests will be developed; these will correspond to the three types of tests set out by Besag and Newell (general tests, focused tests, and tests for the detection of clustering). The associated tests draw primarily, though not exclusively, upon existing tests and results. The principal contributions are based upon the score statistic for focused tests, which has been an important approach to testing for clustering around environmental hazards. The first contribution consists of the formulation of a global statistic for general tests that corresponds to focused score statistics, along with an assessment of the distribution of the statistic under the null hypothesis of no raised incidence. The local score statistics used for focused tests will have the property of summing to the global statistic used for the corresponding general test. Attention is also given to the maximum local score statistic for the “test for the detection of clustering”. The critical values of this statistic which are required for testing the null hypothesis are described. Application of the methods is made to leukemia data for central New York State.     

Some statistical and conceptual issues in the detection of low-level environmental pollutants

With increasing concern over chemicals that are potential health hazards at low levels, determination of limits of detection have undergone considerable scrutiny. Most traditional detection limit estimators suffer from extensive statistical and/or conceptual limitations. In this paper, traditional detection limit estimators are described and critically evaluated. Using the terminology of Currie (1968), methods are categorized into decision limits versus detection limits. The methods are further categorized into single concentration design versus calibration design methodologies. While the single concentration design methods are useful for fixing ideas and clarifying definitions, they are shown to be extremely limited in practice since dependence of variability on concentration can neither be estimated or incorporated. Calibration-based detection limit estimators are described, compared and contrasted. Generalizations to non-constant variance, multiple future detection decisions and simultaneous control of Type I and II errors are provided. The various calibration-based methods are illustrated using real data and experimental design issues for detection limit studies discussed.     

Genetic Effects of Habitat Fragmentation on Common Species of Swiss Fen Meadows

Abstract:  The area of Caricion davallianae alliance in Switzerland has been considerably reduced and fragmented during the last 150 years. We assessed the genetic variability, inbreeding level, and among-population differentiation of two common habitat-specific plant species, Carex davalliana SM. and Succisa pratensis Moench, in 18 Caricion davallianae fen meadows subjected to fragmentation. We used a spatial field design of fen systems (six systems total), each consisting of one large habitat island and two small habitat islands. We used allozyme electrophoresis to derive standard genetic parameters ( A, P, H_O, H_E, F_IS, F_ST ). In Carex we identified a consistently lower A in isolated habitat islands; furthermore, H_E was lower in small habitat islands than in large habitat islands. In Succisa we identified a lower H_O in small habitat islands than in larger ones. Small habitat islands were marginally significantly differentiated (  F_ST ) from large islands for Succisa . For both species, no effects were evident for F_IS ; therefore, we argue that genetic drift rather than inbreeding is the main cause of the observed differences. The genetic structure of Carex and Succisa in small habitat islands differed from that in large habitat islands, but differences were small. It appears that the observed differences in genetic variability among fen meadows correspond to observed differences in fitness and demographic traits. We show that habitat fragmentation affects not only the rare species in an ecosystem but also reduces the survival probabilities of common species. One of the main goals of conservation should be to mitigate fragmentation of natural habitats in order to increase population sizes and connectivity.     

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.     

Bayesian areal wombling via adjacency modeling

Recently, public health professionals and other geostatistical researchers have shown increasing interest in boundary analysis, the detection or testing of zones or boundaries that reveal sharp changes in the values of spatially oriented variables. For areal data (i.e., data which consist only of sums or averages over geopolitical regions), Lu and Carlin (Geogr Anal 37: 265–285, 2005) suggested a fully model-based framework for areal wombling using Bayesian hierarchical models with posterior summaries computed using Markov chain Monte Carlo (MCMC) methods, and showed the approach to have advantages over existing non-stochastic alternatives. In this paper, we develop Bayesian areal boundary analysis methods that estimate the spatial neighborhood structure using the value of the process in each region and other variables that indicate how similar two regions are. Boundaries may then be determined by the posterior distribution of either this estimated neighborhood structure or the regional mean response differences themselves. Our methods do require several assumptions (including an appropriate prior distribution, a normal spatial random effect distribution, and a Bernoulli distribution for a set of spatial weights), but also deliver more in terms of full posterior inference for the boundary segments (e.g., direct probability statements regarding the probability that a particular border segment is part of the boundary). We illustrate three different remedies for the computing difficulties encountered in implementing our method. We use simulation to compare among existing purely algorithmic approaches, the Lu and Carlin (2005) method, and our new adjacency modeling methods. We also illustrate more practical modeling issues (e.g., covariate selection) in the context of a breast cancer late detection data set collected at the county level in the state of Minnesota.     

The National Resources Inventory: a long-term multi-resource monitoring programme

Interest in natural resources and the environment has led to the development of new federal monitoring efforts, the expansion of existing federal inventory programmes, and discussions of inter-agency collaboration for natural resource assessment data collection. As federal programmes evolve, knowledge gained from existing long-term survey programmes can provide valuable contributions to statistical and operational aspects of survey efforts. This paper describes the National Resources Inventory (NRI), which has been conducted by the US Department of Agriculture's Natural Resources Conservation Service in cooperation with the Iowa State University Statistical Laboratory for several decades. The current NRI is a longitudinal survey of soil, water, and related environmental resources designed to assess conditions and trends every five years on non-federal US lands. An historical overview is provided highlighting the development of the survey programme. Sample design, data collection, and estimation procedures used in the 1992 NRI are described, and statistical issues related to long-term monitoring are discussed.