Using hidden Markov chains and empirical Bayes change-point estimation for transect data

Consider a lattice of locations in one dimension at which data are observed. We model the data as a random hierarchical process. The hidden process is assumed to have a (prior) distribution that is derived from a two-state Markov chain. The states correspond to the mean values (high and low) of the observed data. Conditional on the states, the observations are modelled, for example, as independent Gaussian random variables with identical variances. In this model, there are four free parameters: the Gaussian variance, the high and low mean values, and the transition probability in the Markov chain. A parametric empirical Bayes approach requires estimation of these four parameters from the marginal (unconditional) distribution of the data and we use the EM-algorithm to do this. From the posterior of the hidden process, we use simulated annealing to find the maximum a posteriori (MAP) estimate. Using a Gibbs sampler, we also obtain the maximum marginal posterior probability (MMPP) estimate of the hidden process. We use these methods to determine where change-points occur in spatial transects through grassland vegetation, a problem of considerable interest to plant ecologists.     

How does the spatial structure of habitat loss affect the eco-epidemic dynamics?

Habitat loss is considered as one of the primary causes of species extinction, especially for a species that also suffers from an epidemic disease. Little attention has been paid to the combined effect of habitat loss and epidemic transmission on the species spatiotemporal dynamics. Here, a spatial model of the parasite–host/prey–predator eco-epidemiological system with habitat loss was studied. Habitat patches in the model, instead of undergoing a random loss, were spatially clustered by different degrees. Not only the quantity of habitat loss but also its clustering degree was shown to affect the equilibrium of the system. The infection rate and the probability of successful predation were keys to determine the spatial patterns of species. The epidemic disease is more likely to break out if only a small amount of suitable patches were lost. Counter-intuitively, infected preys are more sensitive to habitat loss than predators if the lost patches are highly clustered. This result is new to eco-epidemiology and implies a possibility of using spatial arrangement of suitable (or unsuitable) patches to control the spread of epidemics in the ecological system.     

A derivation of the statistical characteristics of forest fires

The analysis of large data sets concerning fires in various forested areas of the world has pointed out that burned areas can often be described by different power-law distributions for small, medium and large fires and that a scaling law for the time intervals separating successive fires is fulfilled. The attempts of deriving such statistical laws from purely theoretical arguments have not been fully successful so far, most likely because important physical and/or biological factors controlling forest fires were not taken into account. By contrast, the two-layer spatially extended forest model we propose in this paper encapsulates the main characteristics of vegetational growth and fire ignition and propagation, and supports the empirically discovered statistical laws. Since the model is fully deterministic and spatially homogeneous, the emergence of the power and scaling laws does not seem to necessarily require meteorological randomness and geophysical heterogeneity, although these factors certainly amplify the chaoticity of the fires. Moreover, the analysis suggests that the existence of different power-laws for fires of various scale might be due to the two-layer structure of the forest which allows the formation of different kinds of fires, i.e. surface, crown, and mixed fires.     

全国辐射环境监测网络射频综合场强测量比对

在2011年全国辐射环境监测网络射频综合场强项目测量比对中,采用稳健统计方法对36家参比单位的78个比对测量结果进行统计分析。结果表明,全国各监测机构满意结果占87.3%,有问题结果占7.7%,离群结果占5%。对可能影响监测结果的若干因素进行了研究,如仪器型号等,反映了目前全国辐射环境监测网络射频电磁场测量项目的监测能力水平,为进一步开展质保工作提供了科学依据。     

应用稳健统计方法对环境空气臭氧自动监测现场比对核查结果的分析研究

根据2015年9个城市53台现场臭氧分析仪的现场比对核查结果,比较研究了稳健统计方法和一般统计方法在评价国控网臭氧自动监测数据准确性和精密性上的应用。研究表明:稳健统计能够在不剔除异常数据的前提下降低异常值对正确评价臭氧自动监测数据质量的影响,适合评价现场比对核查结果;采用Hubers方法进行稳健统计,2015年国控网臭氧日常浓度点相对偏差的95%置信区间约为-0.1%至4.5%,95%预测区间为-14.0%~18.3%,变异系数约为9.5%,数据质量仍有提升空间。     

A fair comparison between the spatial scan and the Besag–Newell Disease clustering tests

Routine surveillance of a large geographic region for clusters of adverse health events, particularly cancers, often involves small area health data, possibly controlling for exposure information. Many different methods have been proposed to test for the presence of geographical clusters. Two of the most popular methods are the spatial scan method proposed by Kulldorff and that using a fixed number of cases within scanning circles proposed by Besag and Newell. Although the second test is very popular, it has some difficulties. While the scan test controls for the multiple testing problem, the Besag and Newell test does not. Additionally, the latter method requires the setting of several tuning parameters whose values affect the test performance and are subjectively chosen by the user. This creates a difficulty to make a fair comparison between the two methods and it explains why there have been few formal studies evaluating their relative performances. In this paper, we modify the Besag and Newell test allowing for the control of the error type I probability and compare its power with respect to that of the spatial scan test. We used data sets from a publicly available simulated benchmark. We found that the two methods have similar results, except for clusters located in sparsely populated regions, where the spatial scan method presented a better performance.     

PRESENCE AND DISTRIBUTION OF CHLORINATED ORGANIC COMPOUNDS IN STREAMBED SEDIMENTS,NEW JERSEY1

ABSTRACT: Concentrations of 18 hydrophobic chlorinated organic compounds in streambed sediments from 100 sites throughout New Jersey were examined to determine (1) which compounds were detected most frequently, (2) whether detection frequencies differed among selected drainage basins, and (3) whether concentrations differed significantly among selected drainage basins. Twelve drainage basins across New Jersey that contain a range of land-use patterns and population densities were selected to represent various types and degrees of development. To ensure an adequate number of samples for statistical comparison among drainage basins, the 12 selected basins were consolidated into seven drainage areas on the basis of similarities in land-use patterns and population densities. Additionally, data for three classes of chlorinated organic compounds in streambed sediments from 255 sites throughout New Jersey were examined to determine whether the presence of these compounds in streambed sediments is related to the type and degree of development within the drainage area of each sampling site. Chlorinated organic compounds detected most frequently within the seven representative drainage areas were DDT, DDE, DDD, chlordane, dieldrin, and PCBs. DDT, DDE, and DDD, which were the most widely distributed organic compounds, were detected in about 60 to 100 percent of the samples from all drainage areas but one (where the detection rate for these compounds was about 20 to 40 percent). Chiordane and dieldrin were detected in about 80 to 100 percent of samples from highly urbanized and populated drainage areas; detection frequencies for these compounds tended to be smaller in less developed and populated areas. PCBs were detected in about 40 to 85 percent of samples from all drainage areas; detection frequencies were highest in the most heavily developed and populated areas. Analysis of variance on rank-transformed organic compound concentrations normalized to sediment organic carbon content was used to evaluate differences in concentrations among the seven representative drainage areas. Chlordane and PCBs were the chlorinated organic compounds with the most highly elevated concentrations in streambed sediments across the State. Median normalized concentrations of all six of the most frequently detected chlorinated organic compounds were highest in the most heavily urbanized and populated drainage area and lowest in the less populated, predominantly agricultural or forested areas. Concentrations of DDT and DDE, however, did not differ significantly among most of the drainage areas. Concentrations of DDD, chlordane, dieldrin, and PCBs differed significantly among drainage areas. The highest median normalized concentrations were found in samples from the most heavily urbanized and populated areas, and the lowest were in samples from the least developed, most heavily forested area. Logistic regression was used to examine relations between the presence of hydrophobic chlorinated organic compounds in streambed sediments at specified concentrations and variables that characterize the type and degree of development within the drainage areas of 255 sites across New Jersey. The explanatory variables found most useful for predicting the presence of chlorinated organic compounds in streambed sediments include total population and amounts (in square kilometers) of various land-use categories. Logistic regression equations were developed to identify significant relations between population and amounts of specific land-use categories within drainage areas and the probability of detecting chlorinated organic contaminants in streambed sediments. These relations can be used to assist in the identification of geographic regions of primary concern for contamination of bed sediments by chlorinated organic compounds across the State.     

2009年9-10月国内环境事件

简要统计了2009年9-10月国内发生的各种环境事件94起,包括沙尘天气5起,污染事件13起,地震47起,山体滑坡和泥石流15起,旱灾3起以及其他自然灾害11起.     

长江水系河流沉积物重金属元素含量的计算方法研究

采用长江水系约２６０个背景样点沉积物原样和小于６３μｍ细粒沉积物中１１种重金属元素（铜、铅、锌、镉、汞、钴、镍、砷、铬、锰和铁）含量的数据，研究了数据的频率分布特征和变异系数，比较了算术均值、几何均值和中位数与由Ｂｏｘ－Ｃｏｘ变换而得到的对称均值间的大小关系，结果表明，大多数重金属元素含量服从对数正态分布；采用算术均值表示均值会有较大的偏差，且这种偏差随变异系数的增大而增大；采用中位数偏差较小，但     

溶质运移的空间信息统计组合分析

空间信息统计分析理论与方法能够将空间结构性和随机性有机地结合起来,应用变异函数理论模型、方向综合变异指标以及各种空间最优估计方法,对地下水环境评价参数空间分布的不确定性评价方面,较经典统计方法更为合理。