Dihimpun dan diabstraksikan: Smno.psl-ppsub.agst2012 ENVIRONMETRIKA.

KOMPENDIUMENVIRONMETRIK

Dihimpun dan diabstraksikan: Smno.psl-ppsub.agst2012

ENVIRONMETRIKA

Diunduh dari: http://www.environmetrics.org/ …… 1/9/2012

The International Environmetrics Society (TIES)

The International Environmetrics Society (TIES) is a non-profit organization aimed to foster the development and use of statistical and other quantitative methods in the environmental sciences, environmental engineering

and environmental monitoring and protection.

To this end, the Society promotes the participation of statisticians, mathematicians, scientists and engineers in the solution of environmental problems and emphasizes the need for collaboration and for clear communication

between individuals from different disciplines and between researchers and practitioners.

The Society further promotes these objectives by conducting meetings and producing publications, and by

encouraging a broad membership of statisticians, mathematicians, engineers, scientists and others interested in furthering the role of statistical and

mathematical techniques in service to the environment.

Diunduh dari: http://www.nrcse.washington.edu/ties/journal/journal.html…… 1/9/2012

Environmetrics

Environmetrics, the official journal of The International Environmetrics Society (TIES), an Association of the International Statistical Institute, is devoted to the dissemination of high-quality quantitative research in the

environmental sciences, broadly construed. The journal welcomes pertinent and innovative submissions from applied mathematics,

engineering and signal processing, statistics, risk analysis, and other quantitative disciplines. Articles must answer important scientific

questions in the environmental sciences or develop novel methodology with clear applications to environmental science. New methodology

should be illustrated with recent environmental data.

EnvironmetricsThe official journal of The International Environmetrics Society

(TIES).Aims and Scope

It is a multidisciplinary journal that publishes refereed papers on the development and application of quantitative methods in the

environmental sciences. The scope covers a broad range of statistical, mathematical and engineering topics dealing with the analysis of environmental changes and their impacts on humans and various life forms and ecological relationships. Therefore, the journal welcomes a wide diversity of applications in such

areas as water and air quality, regulation and control, risk and impact analysis, waste management, transboundary pollution,

health aspects of pollution, monitoring, field and laboratory quality control and climatic changes. In addition to publishing

significant research and review papers, Environmetrics publishes book reviews, software reviews, descriptions of data sources and

notices of general interest.

Editors-in-Chief: Peter Guttorp and Walter W. Piegorsch Impact Factor: 1.06

ISI Journal Citation Reports © Ranking: 2011: 41/92 (Mathematics Interdisciplinary Applications); 45/116 (Statistics & Probability);

139/205 (Environmental Sciences)Online ISSN: 1099-095X

Diunduh dari: http://cran.r-project.org/web/views/Environmetrics.html…… 3/9/2012

. Modelling species responses and other data

Analysing species response curves or modeling other data often involves the fitting of standard statistical models to ecological data and includes simple (multiple) regression, Generalised Linear Models (GLM), extended regression (e.g. Generalised Least Squares [GLS]), Generalised Additive

Models (GAM), and mixed effects models, amongst others.

Tree-based models

Tree-based models are being increasingly used in ecology, particularly for their ability to fit flexible models to

complex data sets and the simple, intuitive output of the tree structure. Ensemble methods such as bagging,

boosting and random forests are advocated for improving predictions from tree-based models and to provide information on uncertainty in regression models or

classifiers. Tree-structured models for regression, classification and

survival analysis

Ordination methods, many of which are specialised techniques particularly suited to the analysis of species data:

1. Principal Components (PCA) is used in the climate and climate change fields is Empirical Orthogonal Function (EOF) analysis.

2. Redundancy Analysis (RDA) 3. Canonical Correspondence Analysis (CCA) 4. Detrended Correspondence Analysis (DCA) 5. Principal coordinates analysis (PCO) 6. Non-Metric multi-Dimensional Scaling (NMDS)7. Coinertia analysis 8. Co-correspondence analysis to relate two ecological species data

matrices 9. Canonical Correlation Analysis (CCoA - not to be confused with

CCA, above) 10. Procrustes rotation providing functions to test the significance of

the association between ordination configurations (as assessed by Procrustes rotation) using permutation/randomisation and Monte Carlo methods.

11. Constrained Analysis of Principal Coordinates (CAP)12. Constrained Quadratic Ordination (CQO; formerly known as

Canonical Gaussian Ordination (CGO)

Diunduh dari: http://cran.r-project.org/web/views/Environmetrics.html…… 3/9/2012

. Cluster analysis Cluster analysis aims to identify groups of samples within multivariate data sets. A large range of approaches to this problem have been suggested, but the main techniques are hierarchical cluster analysis, partitioning methods, such as k -means, and finite mixture models or model-based clustering. In the machine learning literature, cluster analysis is an unsupervised learning problem. 1. Hierarchical cluster analysis2. Partitioning methods3. Mixture models and model-based cluster analysis

Ecological theory There is a growing number of packages and books that focus on the use of R for theoretical ecological models.

Population dynamics Estimating animal abundance and related parameters This ection concerns estimation of population parameters (population size, density, survival probability, site occupancy etc.) by methods that allow for incomplete detection. Many of these methods use data on marked animals, variously called 'capture-recapture', 'mark-recapture' or 'capture-mark-recapture' data.

Modelling population growth rates:

It can be used to construct and analyse age- or stage-specific matrix population models.

It contains functions for simulating future forest conditions under different silvicultural regimes using the growth model.

Diunduh dari: http://www.uoguelph.ca/ses/content/environmetrics-modelling …… 4/9/2012

. ENVIRONMETRICS & MODELLING

One of the ongoing endeavours of the School of Environmental Sciences is the development of improved measures or metrics

for quantifying environmental patterns and processes.

Armed with an increasingly sophisticated set of metrics, environmental scientists will be in a better position to discovery

new patterns or trends and their underlying causes.

Modelling is useful for the discovery of knowledge, but is also a predictive tool for forecasting adaptation, mitigation and/or

production strategies in response to changing environments.

Environmetrics and modelling is a transdisciplinary research area and several faculty are members of the

Biophysics Interdisciplinary Group (BIG).

http://biophysics.uoguelph.ca/central/graduate.htm

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/env.3170010107/abstract …… 3/9/2012

. Ill-conditioned information matrices, generalized linear models and estimation of the effects of acid rain

Eric P. Smith1, Brian D. Marx Environmetrics. Volume 1, Issue 1, pages 57–71, 1990

. The problem of acid rain deposition has generated much interest in the modelling and estimation of the effects of acid rain. Recent studies in the northeastern United States have

focused on the question of trends in lake acidity and the effects on aquatic organisms, especially fish.

One approach has been to model the presence or absence of fish species as a function of relevant environmental variables.

As the number of these explanatory variables may be large, there is concern about redundancies and collinearities. Because the

model used is a special case of generalized linear models, standard approaches to assessment and adjustment for

collinearity may be misleading.

Estimation of parameters in the generalized linear model involve an interative method of solution. The important parameter is the

information matrix. Illconditioning of this matrix, as caused by collinearity has severe effects on parameter and variance

estimates.

To asssess the effects of collinearities, some new diagnostics are presented. Two techniques for estimating parameters in the

presence of multicollinearity; the ridge estimator and the principal component method, are extended to the generalized

linear model.

http://onlinelibrary.wiley.com/doi/10.1002/env.v1:1/issuetoc

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/env.3170010301/abstract…… 3/9/2012

. Model selection for environmental dataJun Bai1, Anthony J. Jakeman2, Michael McAleer

Environmetrics. Volume 1, Issue 3, pages 211–254, 1990

. A practical approach is proposed for model selection and discrimination among nested and non-nested probability

distributions. Some existing problems with traditional model selection approaches are addressed, including standard testing of a null hypothesis against a more general alternative and the use

of some well-known discrimination criteria for non-nested distributions.

A generalized information criterion (GIC) is used to choose from two or more model structures or probability distributions. For each set of random samples, all model structures that do not perform

significantly worse than other candidates are selected.

The two-and three-parameter gamma, Weibull and lognormal distributions are used to compare the discrimination procedures

with traditional approaches. Monte Carlo experiments are employed to examine the performances of the criteria and tests

over large sets of finite samples.

For each distribution, the Monte Carlo procedure is undertaken for various representative sets of parameter values which are

encountered in fitting environmental quality data.



Asymptotic confidence intervals from a preliminary test estimatorS. E. Ahmed1, R. J. Kulperger

EnvironmetricsVolume 1, Issue 3, pages 295–303, 1990

A preliminary test estimator is a method of combining information from two experiments in a problem of

estimating a parameter.

The asymptotics of this estimator in the case of estimating a population mean is considered in a setting of

a local alternative. Asymptotic confidence intervals are obtained using the asymptotic distribution.



Non-linear mixed regression modelsRichard T. Burnett, W. H. Ross, Daniel Krewski

Environmetrics. Volume 6, Issue 1, pages 85–99, January/February 1995

In this paper we present an estimating equation approach to statistical inference for non-linear random effects regression models

for correlated data.

With this approach, the distribution of the observations and the random effects need not be specified; only their expectation and

covariance structure are required.

The variance of the data given the random effects may depend on the conditional expectation.

An approximation to the conditional expectation about the fitted value of the random effects is used to obtain closed form

expressions for the unconditional mean and covariance of the data.

The proposed methods are illustrated using data from a mouse skin painting experiment.



. A new model pdf for contaminants dispersing in the atmosphereD. M. Lewis, P. C. Chatwin

Environmetrics. Special Issue: New Statistical Methods in Turbulent Diffusion

Volume 6, Issue 6, pages 583–593, November/December 1995

This paper illustrates the modelling of the probability density function for the concentration of a scalar

dispersing in the atmosphere, using a simple modification of a two state distribution relevant to the hypothetical case of no molecular diffusion.

The low concentration values are modelled by means of an exponential distribution, and the high concentration tails by a generalized Pareto

distribution.

The fits are generally better than those obtained using the beta distribution considered in earlier work.

The new model links well with the α-β theory for concentration moments in turbulent flows


Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/%28SICI%291099-095X%28200001/02%2911:1%3C99::AID-ENV391%3E3.0.CO;2-4/abstract …… 3/9/2012

Statistical modeling of sediment and oyster PAH contamination data collected at a South Carolina estuary (complete and left-

censored samples)R. E. Thompson1, E. O. Voit1,*, G. I. Scott

Environmetrics. Volume 11, Issue 1, pages 99–119, January/February 2000

. This paper presents an analysis of polycyclic aromatic hydrocarbon (PAH) sediment and oyster contamination data

collected at Murrells Inlet, South Carolina. Murrells Inlet is a high salinity estuary located in a heavily urbanized area south of Myrtle

Beach, South Carolina.

In the first part, lognormal and Weibull distributions are determined that best fit the data, as measured by P–P and Q–Q

probability plots.

The results indicate that the Weibull gives an adequate fit for almost all the PAH analytes considered. In fact, the Weibull almost

always provides a better fit to the data than the lognormal distribution.

The second part addresses issues associated with non-detection points, as they are regularly encountered in environmental

analyses.

In statistical terms, the existence of non-detection points corresponds to data that are left-censored. Several statistical

methods for estimating the Weibull parameters from such left-censored data are explored.

The overall result is in agreement with recent findings reported by other investigators: methods based on the underlying distribution of the data give more consistent results than those obtained by

commonly used substitution methods.

http://onlinelibrary.wiley.com/doi/10.1002/(SICI)1099-095X(200001/02)11:1%3C%3E1.0.CO;2-T/issuetoc

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/%28SICI%291099-095X%28200005/06%2911:3%3C271::AID-ENV407%3E3.0.CO;2-T/abstract…… 3/9/2012

Parametric empirical Bayes estimation for a class of extended log-linear regression models

Wanzhu Tu1,*, Walter W. PiegorschEnvironmetrics. Volume 11, Issue 3, pages 271–285, May/June 2000

This paper presents a fully parametric empirical Bayes approach for the analysis of count data, with emphasis on its application

to environmental toxicity data.

A hierarchical structure for the mean response is developed from a generalized linear model, based on a Poisson distribution. The linear predictor is embedded at the prior level of the hierarchy. This allows for enhanced flexibility when accounting for extra-

Poisson variation, which is often displayed with count data from environmental bioassays.

The model expands upon the traditional log-linear model in two different ways: (1) it extends the Poisson distributional

assumption; and (2) it incorporates an extended family of link functions that includes the log link as a special case.

The main advantage of this approach is that it combines relative computational simplicity with hierarchical modeling flexibility. In

this paper, we emphasize the model's development and the practical issues related to the analysis.

We describe an application of the proposed model to data from an environmental mutagenesis experiment.

http://onlinelibrary.wiley.com/doi/10.1002/(SICI)1099-095X(200005/06)11:3%3C%3E1.0.CO;2-B/issuetoc

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/%28SICI%291099-095X%28200005/06%2911:3%3C341::AID-ENV421%3E3.0.CO;2-8/abstract…… 3/9/2012

Application of a local linear autoregressive model to BOD time series

Zongwu Cai, Ram C. TiwariEnvironmetrics

Volume 11, Issue 3, pages 341–350, May/June 2000

In this paper, we analyze the biochemical oxygen demand data collected over two years from McDowell Creek, Charlotte, North Carolina, U.S.A., by fitting an autoregressive model with time-

dependent coefficients.

The local linear smoothing technique is developed and implemented to estimate the coefficient functions of the autoregressive model.

A nonparametric version of the Akaike information criterion is developed to determine the order of the model and to select the

optimal bandwidth.

We also propose a hypothesis testing technique, based on the residual sum of squares and F-test, to detect whether certain

coefficients in the model are really varying or whether any variables are significant.

The approximate null distributions of the test are provided.

The proposed model has some advantages, such as it is determined completely by data, it is easily implemented and it provides a better

prediction.

http://onlinelibrary.wiley.com/doi/10.1002/(SICI)1099-095X(200005/06)11:3%3C%3E1.0.CO;2-B/issuetoc


Spatiotemporal models in the estimation of area precipitation

Eduardo Severino, Teresa AlpuimEnvironmetrics

Volume 16, Issue 8, pages 773–802, December 2005

Since area precipitation measurements are difficult to obtain because of the large spatial and time variability of the precipitation

field, the development of statistical methods for the optimal combination of weather radar and rain gauge measurements is a

matter of great importance.

This work presents area rainfall prediction methods based on kriging and cokriging techniques modified to account for the

autoregressive temporal structure of the gauge measurement process.

Hence, the suggested kriging-type predictor includes spatial observations both at the present time and at k lagged time

instants. Such predictors are called of kth-order. Cokriging-type predictors developed in this article include the mixed cokriging and

linkage cokriging predictors. Mixed cokriging combines 1st-order prediction and observations of a co-process. The linkage cokriging predictor is appropriate to deal

with observations from any two different processes with proportional, yet unknown, expected values. This will be the case

for the spatiotemporal models adopted in this work to describe rain gauges and radar measurements. Its expression is the same as the simple cokriging, but the usual conditions are replaced by a single

linkage condition.

Finally, we apply these methods to a storm of mixed type that occurred in 1992, for 99 h, over the Alenquer River basin region

located north of Lisbon.



Evaluating the impact of pollution on plant–Lepidoptera relationships

Christian Mulder*, Tom Aldenberg, Dick de Zwart, Harm J. van Wijnen, Anton M. BreureEnvironmetrics

Volume 16, Issue 4, pages 357–373, June 2005

We monitored the biodiversity of plants, adult butterflies and leaf-miners in a Dutch nature reserve over a period of six years (1994–

1999) within the International Co-operative Programme on Integrated Monitoring on Air Pollution Effects (ICP-IM).

Butterfly abundance decreased steadily over the period, indicating a negative diversity trend, while the number of leaf-mining larvae

of Microlepidoptera remained fairly constant. Also the concentration of pollutants (NH4, NO3, SO4, Cd, Cu and Zn) was

determined in air, leaves, litter, throughfall and stemflow.

We have no reason to expect a negative impact of acidification in rainwater or climate change, as temperature and ozone show no

significant trends across the six years.

It is shown that the nectar-plants of adult butterflies are much more sensitive to heavy metals than the nectar-plants of moths

and other pollinating insects. It is hypothesized that the butterfly decline is a secondary effect of heavy metal stress on local plants, not resulting in a decrease in the number of host-plants, but in a selective pressure of pollutants on the plant vigour, subsequently

affecting their pollinators (p < 0.001).

An alternative explanation, such as the possible coexistence of a direct effect of xenobiotics on the adult Lepidoptera occurring in

the study area, is not supported by our data (p > 0.05).



Bivariate distributed lag models for the analysis of temperature-by-pollutant interaction effect on mortality

Vito M. R. MuggeoEnvironmetrics

Special Issue: Special Issue: Statistics for Environmental DecisionsVolume 18, Issue 3, pages 231–243, May 2007

This paper introduces Bivariate Distributed Lags Models (BDLMs) to investigate synergic effect of temperature and airborne

particles on mortality. These models seem particulary attractive since they allow to

model interactions between such environmental variables accounting for possible delayed effects.

A B-spline framework is used to approximate the coefficient surface of the temperature-by-pollutant interaction and possible

alternatives are also discussed.

A case study of mortality time-series data in Palermo, Italy, is presented to illustrate the model.



Environmental pollution analysis by dynamic structural equation models

Lara Fontanella, Luigi Ippoliti*, Pasquale ValentiniEnvironmetrics


As requested by the framework EU Directive on air quality assessment and management (96/62/EC) and related ‘daughter’

directives, air quality standards for specific pollutants are designed to protect public health and environment.

Modeling is one of the main activities to evaluate air quality and to prepare future control programs. Of course, this is not an easy task

since a variety of pollutants may undergo chemical reactions between themselves and with other species.

Nevertheless, in this paper we attempt to discuss a framework to construct a multivariate model which is able to capture the

dynamical interactions among pollutants and meteorological variables.

Specifically, assuming that latent or background effects underlying the fluctuation of observations can be estimated, a dynamic

structural equation model is developed in a state-space form.

A research study on the Milan district for data provided by the Lombardia Environmental Protection Agency (ARPA) is presented.



Semiparametric zero-inflated Poisson models with application to animal abundance studies

Monica Chiogna1,*, Carlo GaetanEnvironmetrics


This paper describes a framework for flexibly modeling zero-inflated data. Semiparametric regression based on penalized

regression splines for zero-inflated Poisson models is introduced. Moreover, an EM-type algorithm is developed to perform

maximum likelihood estimation.

As an illustration, a study of animal abundance is tackled. In fact, abundance often shows excess of zeroes and is a complicated

function of the explanatory variables.

In particular, the relationships between avian abundance and environmental variables indicating land use are tackled.


Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/env.1132/full …… 3/9/2012

Optimal design for detecting dependencies with an application in spatial ecology

Werner G. Müller, Juan M. Rodríguez-Díaz, María J. Rivas LópezEnvironmetrics

Special Issue: Spatio-Temporal Stochastic Modelling. (METMAV)Volume 23, Issue 1, pages 37–45, February 2012

. The paper is concerned with further developing a spatial sampling method based upon optimal design concepts motivated by an

application in the area of biodiversity monitoring.

Statistical techniques for detecting spatial patterns in the distribution of species richness now have some long tradition in this

field, specifically the use of correlograms.

The issue of where (and when) to undertake observations has, but only rarely, been treated. In this paper, we aim to extend the existing literature with techniques of finding good designs to

optimize the power of tests for spatial dependence.

Special emphasis will be given to the difference in using the exact distribution of Moran's and its normal approximation in this context. We uncover the remarkable effect that the use of optimal designs

tends to improve the normal approximation. Two illustrative artificial examples will be followed by a real case

analysis from the ecological literature.

http://onlinelibrary.wiley.com/doi/10.1002/env.v23.1/issuetoc

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1111/j.1538-4632.2009.00736.x/abstract …… 3/9/2012

DESIGNS FOR DETECTING SPATIAL DEPENDENCEDaniela Gumprecht1, Werner G. Müller2, Juan M. Rodríguez-Díaz

Geographical Analysis. Volume 41, Issue 2, pages 127–143, April 2009

The aim of this article is to find optimal or nearly optimal designs for experiments to detect spatial dependence that

might be in the data. The questions to be answered are: how to optimally select

predictor values to detect the spatial structure (if it is existent) and how to avoid to spuriously detect spatial dependence if

there is no such structure.

The starting point of this analysis involves two different linear regression models: (1) an ordinary linear regression model with

i.i.d. error terms—the nonspatial case and (2) a regression model with a spatially autocorrelated error term, a so-called

simultaneous spatial autoregressive error model.

The procedure can be divided into two main parts: The first is use of an exchange algorithm to find the optimal design for the respective data collection process; for its evaluation an artificial data set was generated and used. The second is estimation of

the parameters of the regression model and calculation of Moran's I, which is used as an indicator for spatial dependence

in the data set.

The method is illustrated by applying it to a well-known case study in spatial analysis.

http://onlinelibrary.wiley.com/doi/10.1111/gean.2009.41.issue-2/issuetoc

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1111/j.1538-4632.2009.00766.x/abstract …… 3/9/2012

Spatial Autocorrelation in Ecological Studies: A Legacy of Solutions and Myths

Marie-Josée Fortin1, Mark R.T. DaleGeographical Analysis

Special Issue: A 40th Anniversary Celebration of A. Cliff and J. Ord, 1969, The Problem of Spatial Autocorrelation

Volume 41, Issue 4, pages 392–397, October 2009

A major aim of including the spatial component in ecological studies is to characterize the nature and intensity of spatial relationships between organisms and their environment.

The growing awareness by ecologists of the importance of including spatial structure in ecological studies (for hypothesis development, experimental design, statistical analyses, and

spatial modeling) is beneficial because it promotes more effective research.

Unfortunately, as more researchers perform spatial analysis, some misconceptions about the virtues of spatial statistics have

been carried through the process and years. Some of these statistical concepts and challenges were already presented by

Cliff and Ord in 1969.

Here, we classify the most common misconceptions about spatial autocorrelation into three categories of challenges: (1)

those that have no solutions, (2) those where solutions exist but are not well known, and (3) those where solutions have been

proposed but are incorrect.

We conclude in stressing where new research is needed to address these challenges.

http://onlinelibrary.wiley.com/doi/10.1111/gean.2009.41.issue-4/issuetoc


. Categorical structured additive regression for assessing habitat suitability in the spatial distribution of mussel seed abundance†

M. P. Pata1,2, T. Kneib3, C. Cadarso-Suárez4,*, V. Lustres-Pérez2, E. Fernández-Pulpeiro

Environmetrics. Special Issue: Spatio-Temporal Stochastic Modelling. (METMAV)

Volume 23, Issue 1, pages 75–84, February 2012

Categorical regression models enable the investigation of regression relationships between a polytomous response and a set of regressor variables. Depending on whether the categories

are ordered or nominal, special categorical models such as cumulative and multinomial models have been proposed in the

statistical literature.

In this paper, we compare various categorical structured additive regression (STAR) models for assessing habitat

suitability in the spatial distribution of mussel seed abundance in the Galician coast (northwest Spain).

STAR models allow us to include nonlinear effects of continuous covariates on the basis of penalized splines whereas spatial

effects can be represented via a Markov random field. Inference is based on a mixed model representation that allows for the

simultaneous estimation of regression coefficients and smoothing parameters.

Although cumulative models may seem to be the most natural choice in our application because of the ordinal nature of the

response, multinomial models provide more detailed information on covariate effects as all effects are allowed to

depend on the different categories of mussel seed abundance.

The statistical procedures based on STAR models proved very useful in revealing valuable information towards the application

of adequate management of this marine resource.

http://onlinelibrary.wiley.com/doi/10.1002/env.1140/full







Knowledge on the relationship between species distribution and environmental factors is of crucial interest to ecologists (Guisan

and Zimmermann, 2000; Lehmann et al.2002; Moisen et al.2006). For example, understanding the ecological processes that

determine distributional patterns can be used to develop resource-specific exploitation plans (Underwood et al.2000).

For a long time, generalized linear models have been the most widely used statistical model class for assessing the impact of environmental variables on species distribution, but nowadays, generalized additive models (GAM) become increasingly popular because of their ability to handle nonlinear effects of continuous

covariates.

This GAM is particularly relevant in ecological data where nonlinear covariate effects may obey a better ecological interpretation.

However, GAMs still assume that the responses are conditionally independent while spatial correlation is often present in ecological

data. Structured additive regression (STAR) models allow to overcome this restriction by combining nonlinear covariate effects

with the possibility to correct for spatial autocorrelation via the inclusion of spatial effects.

The spatial effect can additionally be split into a correlated (structured) and an uncorrelated (unstructured) part to separate

overdispersion effects caused by unobserved, spatially unstructured heterogeneity and spatial autocorrelation












STATISTICAL METHODOLOGY: CATEGORICAL STRUCTURED ADDITIVE REGRESSION

Categorical regression models aim at modeling the relationship between regressor variables and a polytomuous response Y ∈ {1, … ,k}. Depending

on the nature of the response, either cumulative regression models for ordered response categories or multinomial regression models for

unordered, nominal responses may be considered. Although ordinal models may seem to be the most natural choice in our application because of the ordinal structure of the response, we also opt for a

multinomial model as the latter enables the inclusion of category-specific covariate effects. In particular, comparing results from both types of

models yields a more informative picture from a biological point of view.For regression modeling, it is advantageous to represent the categorical

response Y in terms of dummy variables y(1), … ,y(k) representing the different response categories such that :

Obviously, one of the dummy variables is redundant, and we can therefore identify one of the categories as reference category and work

only with the remaining q = k −1 dummies.The aim of a categorical regression model can now be formulated as

explaining the probabilities

on the basis of a set of category-specific predictors η(1), … ,η(q) and response functions h(1), … ,h(q) (Fahrmeir and Tutz, 2001). Given the vector of probabilities π = (π(1), … ,π(q)) ′ , the vector of dummy variables y = (y(1),

… ,y(q)) ′ then follows a multinomial distribution, yielding the basis for maximum likelihood estimation of the regression coefficients. Different

types of categorical regression models are obtained by choosing specific predictors and response functions as detailed in the following sections.









Multinomial STAR modelsA multinomial logit model is obtained based on the response function

that extends the well-known binary logit model to the case of categorical responses. It can be motivated from latent utilities associated with the

different response categories via the principle of maximum utility (McFadden, 1973), which is quite common in brand choice modeling.

In a structured additive multinomial logit model adapted to our specific data situation, the predictor is specified as :

where υ ′ α(r) corresponds to parametric effects α(r) of covariates υ,

are smooth, nonlinear functions of continuous covariates x1, … ,xl,

represents correlated spatial effects of regions s ∈ {1, … ,S}, and are unstructured, uncorrelated spatial effects. The separation of the

spatial effect into two contributions reflects the interpretation of spatial effects as proxies for unobserved covariates that either may be spatially varying with a strong spatial structure or may vary only locally. Another

reason to include unstructured spatial effects is to adjust for overdispersion which, however, may also be caused by missing

covariates. All covariate effects are category specific such that a large flexibility is achieved.









. Cumulative STAR models

A cumulative categorical regression model is given by the response function

where F denotes an absolutely continuous cumulative distribution function. An equivalent formulation of the model is

which reveals more clearly why the model is referred to as a cumulative model: It defines a specific form for the cumulative distribution function of

Y. Note that the model assumes that the categories of the response are ordered such that the expression Y ⩽r is indeed meaningful. The most popular choice for the cumulative distribution function F results when

considering the extreme value distribution, which again leads to a logit type model.

The cumulative model can also be motivated from considering latent utilities (see for example (Fahrmeir and Tutz, 2001)). The predictor is

given by

, where − ∞ = θ(0) < … < θ(k) = ∞ is a set of ordered thresholds and

denotes a predictor that is defined in analogy to the predictor of the multinomial model (except that all effects are constant across categories).






M. P. Pata, T. Kneib, C. Cadarso-Suárez, V. Lustres-Pérez, E. Fernández-PulpeiroEnvironmetrics. Special Issue: Spatio-Temporal Stochastic Modelling. (METMAV)


The main aim of this paper was to propose a novel application of different categorical STAR models to the field of marine resources. STAR models enable the inclusion of flexible nonlinear effects of continuous covariates as well as spatial effects in the regression specification. In our application, it turned out that flexible categorical

regression models can be very useful tools for fitting biological data such as mussel seed abundance.

Compared with the ordinal model, the multinomial model provides more insight into the factors that influence the spatial distribution of mussel seed. As the multinomial

model allows for different covariate effects along the various response categories, we can identify whether factors determining the presence of the resource are different from those determining its abundance, which is very important in order to develop

suitable exploitation plans.Estimation in our models was based on an empirical Bayes procedure relying on mixed

model methodology. This approach allows to determine the functional form of covariate effects simultaneously with the estimation of the function complexity (as represented by the smoothing variances). An alternative approach is given by the

Markov chain Monte Carlo simulation techniques. Such models have also been proposed in the literature but are mostly based on probit instead of logit specifications

as these allow to recur to latent Gaussian models via the utility approaches that we considered as a motivation for categorical regression models.

For the sake of illustration, we have only included two continuous covariates (tidal height and magnetic course) in the STAR models considered in this paper. However,

STAR models are of course flexible enough to accommodate (i) more than two continuous and/or categorical covariates (i.e., slope of the site, type of substrate) and

(ii) complex interactions between them.

Interpretation of results drawn from smooth multinomial STAR models is not immediate. For such models to be directly interpreted, employment of an effect

measure, such as the OR, was suggested in this paper. The use of such measure may help the researcher to better understand the effect of the continuous covariates on the

different categories of the response. It may be worth pointing out that although the functional form of the OR for a given predictor does not depend on the value used as reference point, the choice of this point does affect OR values and must be taken into

account in their interpretation.

Finally, an additional advantage of using STAR models for fitting mussel seed data lies in the flexibility of incorporating temporal effects in a straightforward manner. In this

way, it is possible to offer flexible spatio-temporal models, which may provide essential information for carrying out adequate management of this species and other

marine resources with similar distribution patterns.



Diunduh dari: http://www.sciencedirect.com/science/article/pii/S0167947304003214 …… 3/9/2012

. Generalized structured additive regression based on Bayesian P-splines

Andreas Brezger , Stefan LangComputational Statistics & Data Analysis. Volume 50, Issue 4, 24 February

2006, Pages 967–991.

. Generalized additive models (GAM) for modeling nonlinear effects of continuous covariates are now well established tools for

the applied statistician. A Bayesian version of GAM's and extensions to generalized structured additive regression (STAR)

are developed.

One or two dimensional P-splines are used as the main building block. Inference relies on Markov chain Monte Carlo (MCMC)

simulation techniques, and is either based on iteratively weighted least squares (IWLS) proposals or on latent utility representations

of (multi)categorical regression models.

The approach covers the most common univariate response distributions, e.g., the binomial, Poisson or gamma distribution, as

well as multicategorical responses. For the first time, Bayesian semiparametric inference for the widely used multinomial logit

model is presented.

Two applications on the forest health status of trees and a space–time analysis of health insurance data demonstrate the potential

of the approach for realistic modeling of complex problems. Software for the methodology is provided within the public domain

package BayesX.

http://www.sciencedirect.com/science/article/pii/S0167947304003214

http://www.sciencedirect.com/science/article/pii/S0167947304003214

http://www.sciencedirect.com/science/journal/01679473/50/4

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.2307/3236568/abstract …… 3/9/2012

Ordinal response regression models in ecologyAntoine Guisan, Frank E. Harrell

Journal of Vegetation ScienceVolume 11, Issue 5, pages 617–626, October 2000

Although ordinal data are not rare in ecology, ecological studies have, until now, seriously neglected the use of specific ordinal

regression models.

Here, we present three models – the Proportional Odds, the Continuation Ratio and the Stereotype models – that can be

successfully applied to ordinal data. Their differences and respective fields of application are

discussed.

Finally, as an example of application, PO models are used to predict spatial abundance of plant species in a Geographical

Information System.

It shows that ordinal models give as good a result as binary logistic models for predicting presence-absence, but are

additionally able to predict abundance satisfactorily.

http://onlinelibrary.wiley.com/doi/10.1111/jvs.2000.11.issue-5/issuetoc

Diunduh dari: http://markstat.net/en/images/stories/environmetrics.pdf …… 4/9/2012

. . Methodologic issues in linking aggregated environmental andhealth data

Markku Nurminen and Tuula NurminenEnvironmetrics

Vol. 11, No. 1, 2000

Epidemiologic studies of environmental exposures and their impacts on disease risk are an important and increasingly applied approach in public health assessment. However, environmental

epidemiology often uses data that have been collected as temporal-spatial and demographic statistics, and thus are only

available for analysis at the level of aggregate information.

The need to conduct aggregate-level studies springs primarily from the difficulty of obtaining high-quality, individual-level data on

environmental exposures and extraneous covariates.

This paper discusses the special characteristics of aggregate data and explains why great care must be exercised when the links

between environment and health are analyzed.

Further, this paper recalls ways to select an appropriate data-analytic method and strategy for epidemiologic studies, and to

infer whether exposure to an environmental risk factor leads to a specific health outcome. Applicable statistical methods include ecologic analysis, time series analysis, multilevel modeling, and

quantiative risk assessment.

Finally, this paper outlines some methodologic requirements for linking environment and health data.


. Bivariate splines for ozone concentration forecasting

Bree Ettinger, Serge Guillas, Ming-Jun LaiEnvironmetrics. Volume 23, Issue 4, pages 317–328, June 2012

In this paper, we forecast ground level ozone concentrations over the USA, using past spatially distributed measurements and

the functional linear regression model.

We employ bivariate splines defined over triangulations of the relevant region of the USA to implement this functional data

approach in which random surfaces represent ozone concentrations.

We compare the least squares method with penalty to the principal components regression approach. Moderate sample sizes provide good quality forecasts in both cases with little

computational effort. We also illustrate the variability of forecasts owing to the choice of smoothing penalty.

Finally, we compare our predictions with the ones obtained using thin-plate splines. Predictions based on bivariate splines require

less computational time than the ones based on thin-plate splines and are more accurate.

We also quantify the variability in the predictions arising from the variability in the sample using the jackknife, and report that predictions based on bivariate splines are more robust than the

ones based on thin-plate splines.



Threshold models for river flow extremesOlivia Grigg, Jonathan Tawn

Environmetrics. Volume 23, Issue 4, pages 295–305, June 2012

We model extreme river flow data from five UK rivers with distinct hydrological properties. The data exhibit significant and

complex nonstationarity, which we model using a nonlinear function of hydrological covariates corresponding to soil

saturation, latent flow of the river and rainfall.

We additionally consider season as a covariate, although the hydrological covariates explain most of the seasonal effect

directly. The standard approach to modelling data of this kind is to fix a threshold and to model exceedances of this threshold

using the generalised Pareto distribution.

We identify a number of problems with this approach in nonstationary cases. To overcome these issues, we propose the

use of a censored generalised extreme value distribution for threshold exceedances.

The data analysis illustrates a number of features of model fit and in particular the stability of the model parameters and

return levels to threshold choice.


Diunduh dari: http://ukpmc.ac.uk/abstract/MED/17874195 …… 4/9/2012

Environmetrics to evaluate marine environment quality.

Spanos T, Simeonov V, Simeonova P, Apostolidou E, Stratis JEnvironmental Monitoring and Assessment [2008, 143(1-3):215-225]

.The environmetric data analysis of analytical datasets from

sediment and benthic organisms samples collected from different sampling sites along the coast of Black Sea near to City of Varna,

Bulgaria has given some important indications about the bioindication properties of both type of samples.

Various multivariate statistical methods like cluster analysis, principal components analysis, source apportioning modeling and partial least square (PLS) modeling were used in order to classify and interpret the parameters describing the chemical content of

the coastal sediments (major components, heavy metals and total organic carbon) and benthic organisms (heavy metals).

It has been shown that seriously polluted coastal zones are indicated in the same way by all benthic species, although some specificity could be detected for moderate polluted regions' e.g. polychaeta accumulated preferably Co, Cr, Cu, and Pb; crustacea

- As, Cd, and Ni; mollusca - Zn.

The identified latent factors responsible for the dataset structure are clearly indicated and apportioned with respect to their contribution to the total mass or total concentration of the

species in the samples.

The linear regression and PLS models indicated that a reliable forecast about the relation between naturally occurring chemical

components and polluting species accumulated in the benthic organisms is possible.

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Spanos+T%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Spanos+T%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Simeonov+V%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Simeonov+V%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Simeonova+P%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Simeonova+P%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Apostolidou+E%22

http://ukpmc.ac.uk/search/;jsessionid=ccgvsaKYuAu2zSLlN4Tf.0?page=1&query=AUTH:%22Apostolidou+E%22

http://ukpmc.ac.uk/abstract/MED/17874195/?whatizit_url=http://ukpmc.ac.uk/search/?page=1&query=%22PLS%22

http://ukpmc.ac.uk/abstract/MED/17874195/?whatizit_url_Species=http://www.ncbi.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=6341&lvl=0



Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/9780470057339.vae061/abstract ……

4/9/2012

Extreme Value AnalysisSaralees Nadarajah

Published Online: 15 SEP 2006Encyclopedia of Environmetrics

Extreme value theory concerns the behavior of the extremes of a process or processes. The fundamentals of this probability theory have been known since about the beginning of the twentieth century, but the relevant statistical methods for

modeling extreme values emerged in the literature only in the past two decades. In fact, since 1980 the literature has seen a flood of applications of statistical extreme values, covering a

wide range of areas.

The application areas include: environmental sciences, including climate, engineering and hydrology, performance assessment as

in sports or policing, astronomy, finance, chemometrics, mortality studies, and outlier detection. Further references to

specific applications are noted throughout the rest of this entry.

The aim of this article is to review some fundamentals of extreme value theory and relevant statistical methods. The

emphasis will be on the latter and the applications it has attracted in the literature so far. The entry is in two parts. The

first part considers univariate extremes and the remainder is for multivariate extremes. Each part begins with a discussion of

fundamental theoretical results.

This is then followed by a discussion of relevant statistical models, inference and simulation.

Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/9780470057339.vae046/abstract ……

4/9/2012

Epidemic ModelsProfessor Eric Renshaw

Published Online: 15 SEP 2006Encyclopedia of Environmetrics

The importance of studying disease outbreak and spread cannot be overstated. In fourteenth century Europe the Black Death killed

25 million people out of a population of 100 million; the Aztecs lost half their population of 3.5 million from smallpox; whilst

around 20 million people died in the world pandemic of influenza in 1919.

Today the overriding epidemic concern is the spread of human immunodeficiency virus (HIV) acquired immune deficiency syndrome (AIDS), to the considerable detriment of the vast

numbers of people suffering from less mediaconscious diseases such as malaria, schistosomiasis, filariasis, and hookworm

disease.

Parallel problems in marine and agriculturally based environments take a similar toll on plant, animal, and fish populations.

Human attempts to control such epidemiological disasters can themselves lead to further problems e.g. the improper use of

pesticides and management strategies.

Increasing understanding of the underlying processes involved is therefore one of the major environmental problems of our age,

and the best way forward is through the careful use of mathematical modeling.


Testing for space–time interaction in conditional autoregressive models†

M.D. Ugarte, T. Goicoa, J. Etxeberria, A.F. MilitinoEnvironmetrics

Special Issue: Spatio-Temporal Stochastic Modelling. (METMAV)Volume 23, Issue 1, pages 3–11, February 2012

Data on disease incidence or mortality over a set of contiguous regions have been commonly used to describe geographic

patterns of disease, helping epidemiologists and public health researchers to identify possible etiologic factors. Nowadays, the

availability of historical mortality registers offers the possibility of going further, describing the spatio-temporal distribution of risks.

The literature on spatio-temporal modeling of risks is very rich, and it is mainly focused on the use of conditional autoregressive

models from a fully Bayesian perspective.

The complexity of the estimation procedure makes the Empirical Bayes approach a plausible alternative. In this context, it is of interest to test for interaction between space and time, as an absence of space–time interactions simplifies modeling and

interpretation.

In this work, a score test is derived as well as a bootstrap approximation of its null distribution.

A parametric bootstrap test is also provided for comparison purposes.

Results are illustrated using brain cancer mortality data from Spain in the period 1996–2005.

http://onlinelibrary.wiley.com/doi/10.1002/env.1126/abstract



Spatio-temporal disease mapping using INLA†

Birgit Schrödle, Leonhard HeldEnvironmetrics

Special Issue: Handling Complexity and Uncertainty in Environmental Studies, Arising from the TIES-GRASPA Joint Conference Held in Bologna in

2009Volume 22, Issue 6, pages 725–734, September 2011

Spatio-temporal disease mapping models are a popular tool to describe the pattern of disease counts.

They are usually formulated in a hierarchical Bayesian framework with latent Gaussian model. So far, computationally

expensive Markov chain Monte Carlo algorithms have been used for parameter estimation which might induce a large

Monte Carlo error.

An alternative method using integrated nested Laplace approximations (INLA) has recently been proposed. A major

advantage of INLA is that it returns accurate parameter estimates in short computational time. Additionally, the

deviance information criterion is provided for Bayesian model choice.

This paper describes how several parametric and nonparametric models and extensions thereof can be fitted to

space–time count data using INLA.

Particular emphasis is given to the appropriate choice of linear constraints to ensure identifiability of the parameter estimates.

The models are applied to counts of Salmonellosis in cattle reported to the Swiss Federal Veterinary Office 1991–2008.



Diunduh dari: http://onlinelibrary.wiley.com/doi/10.1002/%28SICI%291099-095X%28199905/06%2910:3%3C279::AID-ENV352%3E3.0.CO;2-X/abstract …… 4/9/2012

An exponential family model for clustered multivariate binary dataGeert Molenberghs, Louise M. Ryan

EnvironmetricsVolume 10, Issue 3, pages 279–300, May/June 1999

This paper focuses on the analysis of clustered multivariate binary data that arise from developmental

toxicity studies.

In these studies, pregnant mice are exposed to chemicals to assess possible adverse effects on

developing fetuses.

Multivariate binary outcomes arise when each fetus in a litter is assessed for the presence of malformations

and/or low birth weight.

We analyse the data using a multivariate exponential family model which is flexible in terms of allowing

response rates to depend on cluster size.

Maximum likelihood estimation of model parameters and the construction of score tests for dose effect are

discussed.

http://onlinelibrary.wiley.com/doi/10.1002/(SICI)1099-095X(199905/06)10:3%3C%3E1.0.CO;2-7/issuetoc


Statistical modelling of ecosystem structurePatricia B. CerritoEnvironmetrics

Volume 3, Issue 2, pages 169–181, 1992

In this paper, we provide an example demonstrating a means of modelling the interaction of species in an ecosystem which will enable us to determine long

term growth trends of the various species.

In most cases, the type of interaction between species in an ecosystem is unknown. Therefore it is useful to use a mathematical structure which makes almost no

assumptions as to the form of this interaction.

We use a topological semigroup to model the behavior interaction. To do this, it will be shown how to define the multiplicative structure of the semigroup. Also, it

will be demonstrated how to use kernel density estimation to predict these interactions.



Dynamical model for indoor radon concentration monitoring

Marek Brabec, Karel JílekEnvironmetrics

Special Issue: The 18th TIES Conference: Computational Environmetrics: Protection of Renewable Environment and Human and Ecosystem Health

Volume 20, Issue 6, pages 718–729, September 2009

In this paper, we will deal with interesting example of natural risk modeling – namely of indoor radon concentration, needed for proper

exposure assessment and appreciation of quality of preventive measures taken.

First, we will illustrate, how the traditional view based on fixed (i.e., time-invariant) coefficient models can be misleading. Then we formulate a flexible (nonparametric) regression dynamic model

offering a doable alternative. Situation is not entirely standard here, as the smoothed and weight-giving variables are different.

Nevertheless, estimation for our local regression formulation is easily doable even for rather large data via extension of standard

local smoothing that we describe.

We illustrate on data coming from a rare intensive measurement campaign in an occupied house with simultaneous measurements

taken in different rooms. Our model has nice physical interpretation of its parts. We also illustrate how even such a simple model can

produce behavior that throws some light on radon experts' discussions about natural radon concentration circadial movement phase. This is because our model acts as a linear but time-varying filter that can change not only amplitude but also phase between

different rooms of the same house, suggesting that there might not be a universal phase of (e.g., daily) radon variation. Instead, the

phase might depend on how close a particular indoor location is to the radon sources.

Finally, we present some ideas about how our model can be expanded in future to cover more complicated situations and

settings.



A unified strategy for building simple air quality indices

Francesca Bruno, Daniela CocchiEnvironmetrics

Volume 13, Issue 3, pages 243–261, May 2002

Interest in air quality indices has been increasing in recent years. This is strictly connected with the development and the easy availability of web-communication and on-line information. By

means of web pages it is indeed possible to give quick and easy-to-consult information about air quality in a specific area. We

propose a class of air quality indices which are simple to read and easy to understand by citizens and policy-makers.

They are constructed in order to be able to compare situations that differ in time and space. In particular, interest is focused on situations where many monitoring stations are operating in the

same area. In this case, which occurs frequently, air pollution data are collected according to three dimensions: time, space and type of pollutant. In order to obtain a synthetic value, the dimensions are reduced by means of aggregation processes that occur by

successively applying some aggregating function.

The final index may be influenced by the order of aggregation. The hierarchical aggregation here proposed is based on the successive

selection of order statistics, i.e. on percentiles and on maxima. The variety of pollutants measured in each area imposes a

standardization due to their different effects on the human health.

This evaluation comes from epidemiological studies and influences the final value of the index. We propose to use

simultaneously more than one index of the selected class and to associate a measure of variability with every index. Such

measures of dispersion account for very important additional information.

Copyright © 2002 John Wiley & Sons, Ltd.



Distribution of the maximum in air pollution fieldsSofia Aberg, Peter Guttorp

EnvironmetricsVolume 19, Issue 2, pages 183–208, March 2008

Air quality standards are set to protect public health. The values of the standards are often based on health effect studies, without any statistical considerations. In order to judge if a standard is met measurements of ambient air

quality are taken at monitoring stations, and these measured values are used to decide whether or not the

standard has been violated.

In this paper we examine the statistical quality of some air quality standards by taking both measurement error and variability of the ambient field away from the monitoring

sites into account.

In particular we study the distribution of the maximum of the ambient field conditional on a measured monitoring

value at the value prescribed by the standard.

The distribution of the maximum is computed using a Rice method and relies on a generalization of upcrossings of a

level in one dimension to two dimensions.




Spatial models for flood risk assessmentMarco Bee, Roberto Benedetti, Giuseppe Espa

EnvironmetricsSpecial Issue: Special Issue on Spatial Data Methods for Environmental

and Ecological ProcessesVolume 19, Issue 7, pages 725–741, November 2008

The problem of computing risk measures associated to flood events is extremely important not only from the

point of view of civil protection systems but also because of the necessity for the municipalities of

insuring against the damages.

In this work we propose, in the framework of an integrated strategy, an operating solution which merges

in a conditional approach the information usually available in this setup.

First, we use a logistic auto-logistic model (LAM) for the estimation of the univariate conditional probabilities of

flood events. This approach has two fundamental advantages: it allows to incorporate auxiliary

information and does not require the target variables to be independent. Then we simulate the joint distribution of floodings by means of the Gibbs sampler. Finally, we

propose an algorithm to increase ex post the spatial autocorrelation of the simulated events.

The methodology is shown to be effective by means of an application to the estimation of the flood probability for two partitions of the Italian territory with different

spatial resolution.




Modeling monthly temperature data in Lisbon and PragueTeresa Alpuim, Abdel El-Shaarawi

EnvironmetricsVolume 20, Issue 7, pages 835–852, November 2009

This paper examines monthly average temperature series in two widely separated European cities, Lisbon (1856–1999) and

Prague (1841–2000). The statistical methodology used begins by fitting a straight line to the temperature measurements in each

month of the year. Hence, the 12 intercepts describe the seasonal variation of temperature and the 12 slopes correspond to the rise in temperature in each month of the year. Both cities

show large variations in the monthly slopes.

In view of this, an overall model is constructed to integrate the data of each city. Sine/cosine waves were included as

independent variables to describe the seasonal pattern of temperature, and sine/cosine waves multiplied by time were

used to describe the increase in temperature corresponding to the different months.

The model also takes into account the autoregressive, AR(1), structure that was found in the residuals. A test of the

significance of the variables that describe the variation of the increase in temperature shows that both Lisbon and Prague had

an increase in temperature that is different according to the month. The winter months show a higher increase than the

summer months.




Comparative spatiotemporal analysis of fine particulate matter pollution

W. Pang, G. Christakos , J-F WangEnvironmetrics

Special Issue: Spatio-Temporal Stochastic Modelling: Environmental and Health Processes

Volume 21, Issue 3-4, pages 305–317, May - June 2010

The prime focus of this work is the comparative investigation, theoretical and numerical, of spatiotemporal techniques used in

air pollution studies. Space-time statistics techniques are classified on the basis of a set of criteria and the relative

theoretical merits of each technique are discussed accordingly.

The numerical comparison involves the applications of two representative techniques. For this purpose, the popular

spatiotemporal epistemic knowledge synthesis and graphical user interface (SEKS-GUI) software of spatiotemporal statistics

is used together with a dataset of PM2.5 daily measurements obtained at monitoring stations geographically distributed over

the state of North Carolina, USA.

The analysis offers valuable insight concerning the choice of an appropriate spatiotemporal technique in air pollution studies.


http://onlinelibrary.wiley.com/doi/10.1002/env.v21:3/4/issuetoc


Iterated confirmatory factor analysis for pollution source apportionment†

William F. Christensen, James J. Schauer, Jeff W. LingwallEnvironmetrics

Special Issue: Special Issue on TIES Conference 2004Volume 17, Issue 6, pages 663–681, September 2006

Many approaches for pollution source apportionment have been considered in the literature, most of which are based on the

chemical mass balance equations. The simplest approaches for identifying the pollution source contributions require that the pollution source profiles are known. When little or nothing is known about the nature of the pollution sources, exploratory

factor analysis, confirmatory factor analysis, and other multivariate approaches have been employed.

In recent years, there has been increased interest in more flexible approaches, which assume little knowledge about the

nature of the pollution source profiles, but are still able to produce nonnegative and physically realistic estimates of

pollution source contributions. Confirmatory factor analysis can yield a physically interpretable and uniquely estimable solution, but requires that at least some of the rows of the source profile

matrix be known. In the present discussion, we discuss the iterated confirmatory factor analysis (ICFA) approach.

ICFA can take on aspects of chemical mass balance analysis, exploratory factor analysis, and confirmatory factor analysis by assigning varying degrees of constraint to the elements of the

source profile matrix when iteratively adapting the hypothesized profiles to conform to the data. ICFA is illustrated using PM2.5 data from Washington D.C., and a simulation study illustrates

the relative strengths of ICFA, chemical mass balance approaches, and positive matrix factorization (PMF).




Diunduh dari: http://ukpmc.ac.uk/abstract/MED/19353283 …… 4/9/2012

Environmetric approaches for lake pollution assessment.Simeonova P, Lovchinov V, Dimitrov D, Radulov I

Laboratory for Environmental Physics, Georgi Nadjakov Institute of Solid State Physics, Bulgarian Academy of Sciences, Tzarigradsko Chaussee 72,

1784, Sofia, Bulgaria. [email protected] Monitoring and Assessment [2010, 164(1-4):233-248]

The application of multivariate statistical methods to high mountain lake monitoring data has offered some important

conclusions about the importance of environmetric approaches in lake water pollution assessment.

Various methods like cluster analysis and principal components analysis were used for classification and projection of the data set

from a large number of lakes from Rila Mountain in Bulgaria. Additionally, self-organizing maps of Kohonen were constructed in

order to solve some classification tasks. An effort was made to relate the maps with the input data in order

to detect classification patterns in the data set. Thus, discrimination chemical parameters for each pattern (cluster)

identified were found, which enables better interpretation of the pollution situation.

A methodology for application of a combination of different environmetric methods is suggested as a pathway to interpret

high mountain lake water monitoring data.

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Simeonova+P%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Simeonova+P%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Lovchinov+V%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Lovchinov+V%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Dimitrov+D%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Dimitrov+D%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Radulov+I%22

http://ukpmc.ac.uk/search/?page=1&query=AUTH:%22Radulov+I%22

http://ukpmc.ac.uk/search/?page=1&query=ISSN:%220167-6369%22


Estimating constrained concentration–response functions between air pollution and health

Helen Powell*, Duncan Lee, Adrian BowmanEnvironmetrics


The health risks associated with short-term exposure to air pollution have been the focus of much recent research, most of which has considered linear concentration–response functions

(CRFs) between ambient concentrations of pollution and a health response.

A much smaller number of studies have relaxed this assumption of linearity and allowed the shape of the function to be estimated from the data. However, this increased flexibility has resulted in

CRFs being estimated that appear unfeasible, often showing decreases in the risk to health with increasing concentrations.

Therefore, this paper proposes a Bayesian hierarchical model for estimating constrained CRFs in this context, which is based on

monotonic integrated splines.

These splines produce non-decreasing CRFs, owing to the associated regression parameters being constrained to be non-negative, which we ensure by modelling the latter with a ‘slab

and spike’ prior. The efficacy of our approach is assessed via simulation before

being applied to a study of ozone concentrations and respiratory disease in Greater London between 2000 and 2005.




Estimating constrained concentration–response functions between air pollution and health

Helen Powell*, Duncan Lee, Adrian BowmanEnvironmetrics


The health risks associated with short-term exposure to air pollution have been the focus of much recent research, most of which has considered linear concentration–response functions

(CRFs) between ambient concentrations of pollution and a health response.

A much smaller number of studies have relaxed this assumption of linearity and allowed the shape of the function to be estimated from the data. However, this increased flexibility has resulted in

CRFs being estimated that appear unfeasible, often showing decreases in the risk to health with increasing concentrations.

Therefore, this paper proposes a Bayesian hierarchical model for estimating constrained CRFs in this context, which is based on

monotonic integrated splines.

These splines produce non-decreasing CRFs, owing to the associated regression parameters being constrained to be non-negative, which we ensure by modelling the latter with a ‘slab

and spike’ prior.

The efficacy of our approach is assessed via simulation before being applied to a study of ozone concentrations and respiratory

disease in Greater London between 2000 and 2005.




Water quality monitoring using cluster analysis and linear modelsA. Manuela Gonçalves, Teresa Alpuim.

EnvironmetricsVolume 22, Issue 8, pages 933–945, December 2011

The development of statistical methodologies based on spatial and temporal hydrological data is a very important tool in the

monitoring of surface water quality in a river basin.

This paper uses cluster analysis and linear models to describe hydrological space–time series of quality variables and to detect changes in surface water quality data collected in the River Ave hydrological basin, located in the north-west region of Portugal.

This area receives many untreated effluent discharges from textile industries, which result in extreme pollution. Because of

this problematic environmental situation, local authorities installed a network of 20 monitoring sites, producing monthly measurements of quality variables and later began to operate

three wastewater treatment plants (WTP) at the end of the 1998 hydrological year.

In this work, we propose a two-step methodology to analyse these data which use cluster analysis to classify the quality monitoring sites into spatial homogeneous groups. Then we

adjust linear models to the quality variables associated with the clusters, taking into account the seasonal variations throughout

the year, different trends for each period of time (before and after the installation of WTPs), and the hydro-meteorological

factor.

Finally, statistical tests are performed to evaluate the effective role of the WTPs' performance.




Comparing spatio-temporal models for particulate matter in Piemonte

Michela Cameletti, Rosaria Ignaccolo, Stefano BandeEnvironmetrics

Volume 22, Issue 8, pages 985–996, December 2011

In the last two decades, increasing attention has been given to air pollution around the world, mainly because of its impact on

human health and on the environment. In the Po valley (northern Italy), one of the most troublesome pollutant is PM10 (particulate

matter with an aerodynamic diameter of less than 10 μm). In order to assess PM10 concentration over an entire region,

environmental agencies need models to predict PM10 at unmonitored sites. To choose among possible predictive models and then meet the agencies' request, we focus on the class of

Bayesian hierarchical models as they provide a flexible framework for incorporating relevant covariates as well as

spatio-temporal interactions.

We consider six alternative models for PM10 concentration in Piemonte region (north-western Po Valley), during the winter

season October 2005–March 2006. Our aim is to choose a model that is satisfactory in terms of goodness of fit, interpretability, parsimony, prediction capability and computational costs. In

order to support this choice, we propose a comparison approach based on a set of criteria summarized in a table that can be

easily communicated to non-statisticians.

The comparison findings allow to provide Piemonte environmental agencies with an effective statistical model for building reliable PM10 concentration maps, equipped with the

corresponding uncertainty measure.




Autologistic models for binary data on a latticeJohn Hughes1, Murali Haran2,*, Petruţa C. Caragea

EnvironmetricsVolume 22, Issue 7, pages 857–871, November 2011

The autologistic model is a Markov random field model for spatial binary data. Because it can account for both statistical

dependence among the data and for the effects of potential covariates, the autologistic model is particularly suitable for

problems in many fields, including ecology, where binary responses, indicating the presence or absence of a certain plant or

animal species, are observed over a two-dimensional lattice.

We consider inference and computation for two models: the original autologistic model due to Besag, and the centered

autologistic model proposed recently by Caragea and Kaiser. Parameter estimation and inference for these models is a

notoriously difficult problem due to the complex form of the likelihood function. We study pseudolikelihood (PL), maximum

likelihood (ML), and Bayesian approaches to inference and describe ways to optimize the efficiency of these algorithms and the perfect sampling algorithms upon which they depend, taking

advantage of parallel computing when possible.

We conduct a simulation study to investigate the effects of spatial dependence and lattice size on parameter inference, and find that

inference for regression parameters in the centered model is reliable only for reasonably large lattices (n > 900) and no more

than moderate spatial dependence.

When the lattice is large enough, and the dependence small enough, to permit reliable inference, the three approaches

perform comparably, and so we recommend the PL approach for its easier implementation and much faster execution.




Regression estimator under inverse sampling to estimate arsenic contamination

Mohammad Moradi, Mohammad Salehi, Jennifer Ann Brown, Naser KarimiEnvironmetrics

Volume 22, Issue 7, pages 894–900, November 2011

The fate of arsenic introduced to the environment as a result of the natural and human activities is an important issue. Surveys of arsenic typically involve sampling from

a large area. Measuring arsenic concentrations in samples is expensive, and any improvement in the

survey design is welcome. One way to improve efficiency in sampling is to make use of auxiliary information.

Surveys of environmental pollution can be classed as surveys of rare populations, where there is a large area

with a small polluted subarea. The rare population has many zeroes, or low, values, and contaminated subareas have non-zero, or high, values. Regression estimators or ratio estimators are undefined for those samples containing only information from the

non-rare (zero-value) subpopulation (i.e., the non-contaminated subpopulation) in simple random

sampling. In this paper, we introduce the modified regression estimators and their associated variance

estimators for sampling designs which are suitable for rare populations, such as general inverse sampling and inverse sampling with unequal selection probabilities.

We conducted a simulation study on the real rare population arsenic contamination in Kurdistan. The

simulation results showed that the modified regression estimators are more efficient than the previous

estimators.



The role of statistics in the analysis of ecosystem services

R. I. Smith, J. McP. Dick, E. M. ScottEnvironmetrics

Special Issue: Quantitative Approaches to Ecosystem Service EvaluationVolume 22, Issue 5, pages 608–617, August 2011

Operationalising the holistic approach implicit in an ecosystem services assessment is a challenge, incorporating social and

economic considerations alongside the physical, chemical and biological function of ecosystems. The paper considers the role

of statistics within a range of frameworks proposed for the analysis of ecosystem services.

The use of different statistical techniques within the component parts of an ecosystem services assessment framework are

discussed, including (1) data availability and sampling strategies, (2) statistical data analysis, (3) geography and

spatial models, (4) meta-analysis, (5) environmental models, (6) societal models, (7) feedbacks and loop analysis, and (8)

graphical models including Bayesian belief networks.

Issues of value and the potential for a statistical contribution to multivariate non-monetary valuation are considered.

We argue that statistics has an underpinning role by providing tools to link together the component elements along with their uncertainties for a thorough ecosystem services assessment,

and should be an integral part of this developing inter-disciplinary research area.



Diunduh dari: http://archinte.jamanetwork.com/article.aspx?articleid=1108717 …… 4/9/2012

Ambient Air Pollution and the Risk of Acute Ischemic Stroke

Gregory A. Wellenius, Mary R. Burger, Brent A. Coull, Joel Schwartz, Helen H. Suh, Petros Koutrakis, Gottfried Schlaug, Diane R. Gold, Murray A. Mittleman.

Arch Intern Med. 2012;172(3):229-234.

The link between daily changes in level of ambient fine particulate matter (PM) air pollution (PM <2.5 μm in diameter [PM2.5]) and

cardiovascular morbidity and mortality is well established. Whether PM2.5 levels below current US National Ambient Air Quality Standards

also increase the risk of ischemic stroke remains uncertain.

We reviewed the medical records of 1705 Boston area patients hospitalized with neurologist-confirmed ischemic stroke and abstracted data on the time of symptom onset and clinical

characteristics. The PM2.5 concentrations were measured at a central monitoring station. We used the time-stratified case-crossover study design to assess the association between the risk of ischemic stroke onset and PM2.5 levels in the hours and days preceding each event. We examined whether the association with PM2.5 levels differed by

presumed ischemic stroke pathophysiologic mechanism and patient characteristics.

The estimated odds ratio (OR) of ischemic stroke onset was 1.34 (95% CI, 1.13-1.58) (P < .001) following a 24-hour period classified

as moderate (PM2.5 15-40 μg/m3) by the US Environmental Protection Agency's (EPA) Air Quality Index compared with a 24-hour period

classified as good (≤15 μg/m3). Considering PM2.5 levels as a continuous variable, we found the estimated odds ratio of ischemic

stroke onset to be 1.11 (95% CI, 1.03-1.20) (P = .006) per interquartile range increase in PM2.5 levels (6.4 μg/m3). The increase in risk was greatest within 12 to 14 hours of exposure to PM2.5 and

was most strongly associated with markers of traffic-related pollution.

These results suggest that exposure to PM2.5 levels considered generally safe by the US EPA increase the risk of ischemic stroke

onset within hours of exposure.

Diunduh dari: http://journals.ohiolink.edu/ejc/search.cgi?q=id:03007839/v04i0001/47_irapsrratm&pa

gesize=&mlt=y …… 4/9/2012

The influence of contextual variables on interpersonal spacing.

Worchel, Stephen. Journal of Nonverbal Behavior vol. 10 issue 4 December 1986. p. 230 -

254Four studies examined the effects of contextual variables on interpersonal spacing. Contextual variables were defined as

transitory factors that involved the setting in which an interaction occurs; these variables were delineated from personal and

interpersonal characteristics. In each experimental setting, white male subjects were allowed to choose the distance at which they

interacted with a stranger. The first study found that subjects who had experienced social isolation prior to the interaction chose greater distances than

subjects who had not been isolated. The second study found that subjects chose greater distances when they believed their

interaction would be observed by others than when the interaction was private.

Results from the third study yielded an interaction between topic of conversation and expected length of conversation with greatest

distance being chosen when subjects expected a long conversation to focus on a personal topic. In the final study, room size and shape

influenced interpersonal distance; the interaction indicated that room size affected distance only in rectangular rooms.

The results are discussed in terms of equilibrium model (Argyle & Dean, 1965). It is argued that contextual variables affect intimacy,

and that the equilibrium model can explicate the effects of contextual as well as personal and interpersonal variables.

Diunduh dari: http://journals.ohiolink.edu/ejc/search.cgi?q=id:03007839/v04i0001/47_irapsrratm&pa

gesize=&mlt=y …… 4/9/2012

Interpersonal relationships and personal space: Research review and theoretical model.

Sundstrom, Eric; Altman, Irwin. Human Ecology vol. 4 issue 1 January 1976. p. 47 - 67

This article reviews research concerning interpersonal distance as a function of interpersonal relationships,

attraction, and reactions to spatial invasion.

To integrate research findings, we propose a simple model, based on the idea that people seek an optimal

distance from others that becomes smaller with friends and larger for individuals who do not expect to interact.

The model describes comfort-discomfort as a function of interaction distance in three situations: interacting

friends, interacting strangers, and strangers who do not expect interaction.

These three personal space profiles are discussed in terms of qualifying variables, such as seated vs. standing

interaction, sex composition of the dyad, intimacy of conversation topics, and situational variables.

Diunduh dari: http://journals.ohiolink.edu/ejc/search.cgi?q=keywords:%22Distancing%22&category.facet=Earth%20Sciences&start=211 …… 4/9/2012

Relative vs. absolute statistical analysis of compositions: A comparative study of surface waters of a Mediterranean river.

Otero, N.; Tolosana-Delgado, R.; Soler, A.; Pawlowsky-Glahn, V.; Canals, A. Water Research vol. 39 issue 7 April, 2005. p. 1404-1414

Most hydrogeological research includes some sort of statistical study, which is generally conducted on the raw measures of chemical variables, though there are several theoretical and

practical studies warning against this practice. Arguments refer mainly to the positive character of this type of data, and to the fact

that they carry only information about the relative abundance of each component on the whole, what makes techniques based on

correlation, like the widely used Principal Component Analysis (PCA), loose their meaning.

The solution proposed by Aitchison (1982, Journal of the Royal Statistical Society, Series B 44(2), 139–177)—based on working with

log-ratios of observations—is equivalent to define a new distance between compositions and to adapt usual statistical techniques to

it. To illustrate its effect, our study compares the performance of the biplot—a PCA graphical technique—according to the usual Euclidean

and to the Aitchison distance.

The study is conducted on a set of 14 molarities measured monthly through the years 1997–1999 at 30 different stations along the

Llobregat River and its tributaries (Barcelona, NE Spain). Ordinary analysis, implicitly based on an Euclidean distance, presents some deficiencies, mainly because it only captures major ion variations and the inferred relationship between them actually depends on

other non-relevant variables, such as water mass.

An analysis based on compositional distances captures variations of all the ions; it is robust against the inclusion of non-relevant variables in the analysis; and it offers a way to build factors

expressed as equilibrium equations. In our case, two promising factors are extracted, showing the different anthropogenic and

geological pollution sources of the rivers.


A spatial model to aggregate point-source and nonpoint-source water-quality data for large areas.

White, D.A.; Smith, R.A.; Price, C.V.; Alexander, R.B.; Robinson, K.W. Computers and Geosciences vol. 18 issue 8 September, 1992. p. 1055-

1073

More objective and consistent methods are needed to assess water quality for large areas. A spatial model, one that capitalizes on the topologic relationships among spatial entities, to aggregate pollution sources from upstream drainage areas is described that

can be implemented on land surfaces having heterogeneous water-pollution effects.

An infrastructure of stream networks and drainage basins, derived from 1:250,000-scale digital-elevation models, define the

hydrologic system in this spatial model.

The spatial relationships between point- and nonpoint pollution sources and measurement locations are referenced to the

hydrologic infrastructure with the aid of a geographic information system.

A maximum-branching algorithm has been developed to simulate the effects of distance from a pollutant source to an arbitrary

downstream location, a function traditionally employed in deterministic water quality models.

http://journals.ohiolink.edu/ejc/article.cgi?issn=00983004&issue=v18i0008&article=1055_asmtapnwdfla

http://journals.ohiolink.edu/ejc/article.cgi?issn=00983004&issue=v18i0008&article=1055_asmtapnwdfla


Interpersonal relationships and personal space: Research review and theoretical model.

Sundstrom, Eric; Altman, Irwin. Human Ecology vol. 4 issue 1 January 1976. p. 47 - 67

This article reviews research concerning interpersonal distance as a function of interpersonal relationships,

attraction, and reactions to spatial invasion. To integrate research findings, we propose a simple model,

based on the idea that people seek an optimal distance from others that becomes smaller with friends and larger

for individuals who do not expect to interact.

The model describes comfort-discomfort as a function of interaction distance in three situations: interacting friends,

interacting strangers, and strangers who do not expect interaction.

These three personal space profiles are discussed in terms of qualifying variables, such as seated vs. standing

interaction, sex composition of the dyad, intimacy of conversation topics, and situational variables.


A method for spatial heterogeneity evaluation on landscape pattern of farmland shelterbelt networks: A

case study in midwest of Jilin Province, China. Shi, Xiaoliang; Li, Ying; Deng, Rongxin.

Chinese Geographical Science vol. 21 issue 1 February 2011. p. 48 - 56

On the basis of landscape ecology, combining the Spot 5 high resolution satellite imagery with GIS, a method evaluating the spatial heterogeneity of shelterbelts distribution at landscape

scale is put forward in this paper.

The distance coefficients of reasonable and existing landscape indexes of farmland shelterbelt networks were computed, and then through the classification of the distance coefficients, and the establishment of evaluation rules, the spatial heterogeneity

of farmland shelterbelts was evaluated.

The method can improve the evaluating system of previous studies on shelterbelts distribution, resolve the disadvantages of lacking spatiality of overall evaluation, and make the evaluation

results have more directive significance for shelterbelt management. Based on this method, spatial heterogeneity of

shelterbelt networks was evaluated in the midwest of Jilin Province, China.

The results show that the regions with fewer shelterbelts and no closed network account for 34.7% of the total area, but only 4.9%

of the area has relative reasonable pattern of shelterbelt networks. Many problems exist in the distribution pattern of

shelterbelts, therefore, much attention should be paid to construct farmland shelterbelts in the study area.


Segment transformation in urban tourism. McKercher, Bob.

Tourism Management vol. 29 issue 6 December, 2008. p. 1215-1225

This study tests the proposition that market segments transform unevenly as distance from the source increases. It

builds on distance decay theory by extending the concept to a sub-market or segment-specific level. To date, no research has

examined the transformation of market segments with distance.

The study examines outbound travel by Hong Kong residents to urban destinations in 11 countries/territories.

The study reveals that the aggregate market profile changes with distance, becoming generally older, more affluent and

better educated. However, analysis of share differential of six segments identified through Cluster analysis reveals

substantial differences between them.

Two segments show evidence of segment decay, two show evidence of segment emergence, one shows a polarized segment transformation structure and another shows no

relationship between share and distance.


Characterizing Tourist Sensitivity to Distance. Nicolau, Juan L. Journal of Travel Research vol. 47 issue 1 August 2008. p. 43-52

Literature suggests that the effect of distance on destination choice can be positive or negative, contingent on individual

characteristics.

The aim of this study was to objectively measure, identify, and characterize tourist sensitivities to distance—individual by individual—in a real context where real choices made by

tourists are observed.

The empirical application is carried out on a sample of 2,127 individuals, and the operative formalization used to estimate

the individual sensitivities to distance follows a random-coefficient logit model; to detect the determinant factors,

a regression analysis is used.

After obtaining the sensitivity to distance of each sampled individual, the dimensions that appear to have an effect on it are income, number of children, size of the city of residence, use of intermediaries, transport mode, interest in discovering

new places, variety-seeking behavior, and motivations.

http://journals.ohiolink.edu/ejc/article.cgi?issn=00472875&issue=v47i0001&article=43_ctstd


Spatial modelling in irregularly shaped regions: kriging estuaries.

Rathbun, Stephen L. Environmetrics vol. 9 issue 2 March/April 1998. p. 109 - 129

Estuaries are among the earth’s most valuable and productive environmental resources. To further our understanding of the impact of human activities on estuaries, there is a need for

appropriate statistical methods for analyzing estuarine data. Estuaries possess a number of features that must be considered

during spatial data analyses. Estuaries are irregularly shaped non-convex regions. Therefore, Euclidean distance may not be an appropriate distance metric for spatial analyses of estuaries,

especially if the line segment connecting two sites intercepts land. Furthermore, some environmental variables may take deterministic

values at estuarine boundaries. For example, shorelines are saturated with dissolved oxygen, and the salinity at estuarine

mouths should be close to that of the ocean.

This paper considers methods for spatial modelling and prediction using different distance metrics, and under fixed boundary conditions. These methods are illustrated using data from

Charleston Harbor, an estuary on the coast of South Carolina, USA

© 1998 John Wiley & Sons, Ltd.


Effects of Silviculture Using Best Management Practices on Stream Macroinvertebrate Communities in Three Ecoregions of Arkansas, USA.

McCord, Samuel B.; Grippo, Richard S.; Eagle, Dennis M. Water, Air, and Soil Pollution vol. 184 issue 1-4 September 2007. p. 299 - 311

We examined aquatic macroinvertebrate assemblages in six Arkansas low-order streams across three ecoregions. Samples

were taken at locations above and below silviculture sites using Best Management Practices (BMPs) and were compared in

winter and spring for 1 year prior to logging and 2 years after treatments. Implementation at all sites scored between 89 and 100% in compliance assessments using state BMP guidelines.

Deficiencies were generally limited to engineering controls designed to prevent soil erosion; however, no clear evidence of sedimentation was observed in any of the study streams. Water

quality variables were similar between sites upstream and downstream of the harvests in all survey periods.

Analysis of variance did not indicate reduced taxonomic richness that could clearly be attributed to silviculture

operations, but did reveal several significant differences in relative abundance variables that could be associated with

negative impacts, primarily at a single site.

Euclidean distance indicated that macroinvertebrate assemblage similarity between reference and treatment

stations decreased after treatments at two additional study sites. At most sites, however, there was not an assemblage shift from organisms using coarse particulate organic matter as the

primary food source to those using fine particulate organic matter downstream of the harvests.

Our results indicated that BMPs were moderately to strongly effective in protecting water quality and biological integrity in

five of the six study streams.

http://journals.ohiolink.edu/ejc/article.cgi?issn=00496979&issue=v184i1-4&article=299_eosubmiteoau

http://journals.ohiolink.edu/ejc/article.cgi?issn=00496979&issue=v184i1-4&article=299_eosubmiteoau


A method for spatial heterogeneity evaluation on landscape pattern of farmland shelterbelt networks: A case study in midwest of Jilin Province, China. Shi, Xiaoliang; Li, Ying; Deng, Rongxin. Chinese Geographical Science vol.

21 issue 1 February 2011. p. 48 - 56

On the basis of landscape ecology, combining the Spot 5 high resolution satellite imagery with GIS, a method evaluating the

spatial heterogeneity of shelterbelts distribution at landscape scale is put forward in this paper.

The distance coefficients of reasonable and existing landscape indexes of farmland shelterbelt networks were computed, and then

through the classification of the distance coefficients, and the establishment of evaluation rules, the spatial heterogeneity of

farmland shelterbelts was evaluated.

The method can improve the evaluating system of previous studies on shelterbelts distribution, resolve the disadvantages of lacking spatiality of overall evaluation, and make the evaluation results have more directive significance for shelterbelt management.

Based on this method, spatial heterogeneity of shelterbelt networks was evaluated in the midwest of Jilin Province, China.

The results show that the regions with fewer shelterbelts and no closed network account for 34.7% of the total area, but only 4.9%

of the area has relative reasonable pattern of shelterbelt networks. Many problems exist in the distribution pattern of shelterbelts, therefore, much attention should be paid to construct farmland

shelterbelts in the study area.

http://journals.ohiolink.edu/ejc/article.cgi?issn=10020063&issue=v21i0001&article=48_amfsheimojpc




Concept to assess the human perception of odour by estimating short-time peak concentrations from one-hour mean values. Reply to a comment by Janicke et al. Schauberger, Günther; Piringer, Martin; Schmitzer, Rainer; Kamp, Martin;

Sowa, Andreas; Koch, Roman; Eckhof, Wilfried; Grimm, Ewald; Kypke, Joachim; Hartung, Eberhard. Atmospheric Environment vol. 54 July, 2012.

p. 624-628

Biologically relevant exposure to environmental pollutants often shows a non-linear relationship. For their assessment, as a rule

short term concentrations have to be determined instead of long term mean values. This is also the case for the perception of odour. Regulatory dispersion models like AUSTAL2000 calculate long term mean concentration values (one-hour), but provide no information on the fluctuation from this mean. The ratio between a short term

mean value (relevant for odour perception) and the long term mean value (calculated by the dispersion model), called the peak-to-mean value, is usually used to describe these fluctuations. In general, this

ratio can be defined in different ways.

Janicke et al. (2012), in a comment to Schauberger et al. (2012) which includes a statement that AUSTAL2000 uses a constant factor of 4, argue that AUSTAL2000 does not apply a peak-to-mean factor

and does not calculate odour exceedance probabilities.

Instead it calculates the frequency of so-called odour-hours by applying the relation between the 90-percentile of the

instantaneous concentration and the hourly mean (Janicke and Janicke, 2007a), not between some peak value and the mean.

According to Janicke and Janicke (2007a), the 90-percentile of the instantaneous concentration can in practice be estimated with sufficient accuracy from the hourly mean by using a factor of 4.

Having so far replied to Janicke et al. (2012) we take additionally the opportunity to elaborate a little more on the peak-to-mean concept,

especially pointing out that a constant factor independent of the stability of the atmosphere, the distance from and the geometry of

the source, is not appropriate. On the contrary it shows a sophisticated structure which cannot be described by only one

single value.

http://journals.ohiolink.edu/ejc/article.cgi?issn=13522310&issue=v54inone_c&article=624_ctathptacbje




Least cost distance analysis for spatial interpolation. Greenberg, Jonathan A.; Rueda, Carlos; Hestir, Erin L.; Santos, Maria J.; Ustin, Susan L.

Computers and Geosciences vol. 37 issue 2 February, 2011. p. 272-276

Spatial interpolation allows creation of continuous raster surfaces from a subsample of point-based measurements. Most

interpolation approaches use Euclidean distance measurements between data points to generate predictions of values at unknown locations. However, there are many spatially distributed data sets

that are not properly represented by Euclidean distances and require distance measures which represent their complex

geographic connectivity.

The problem of defining non-Euclidean distances between data points has been solved using the network-based solutions, but

such techniques have historically relied on a network of connected line segments to determine point-to-point distances. While these vector-based solutions are computationally efficient, they cannot

model more complex 2- and 3-dimensional systems of connectivity. Here, we use least-cost-path analyses to define distances between sampled points; a solution that allows for

arbitrarily complex systems of connectivity to be interpolated.

We used least-cost path distances in conjunction with the inverse distance weighting interpolation for a proof-of-concept

interpolation of water temperature data in a complex deltaic river system.

We compare our technique to Euclidean distance interpolation, and demonstrate that our technique, which follows connectivity

rules, yields are more realistic interpolation of water temperature.

http://journals.ohiolink.edu/ejc/article.cgi?issn=00983004&issue=v37i0002&article=272_lcdafsi


Diurnal variation of urban structure in terms of time distance: A spatio-temporal analysis of an urban area.

Itoh, Satoru. GeoJournal vol. 52 issue 3 November 2000. p. 223 - 235

The purpose of this paper is to clarify the diurnal variations in structure of an urban area from the viewpoint of time distance.

To accomplish this, for one entire day, and for the morning, noon, and evening periods, time maps are delineated by using MDS;

also, the indices of accessibility and circuity are computed from the time distances.

As a result, the difference in shape between the time and actual maps becomes clear especially in the morning and also in the evening. Both the accessibility and circuity measured from the time distance show a concentrically shaped pattern where the regional disparity is especially distinct within the morning and

evening periods.

The diurnal variations as described above are thought to occur against the backdrop of the topological traffic conditions within

the study area.

http://journals.ohiolink.edu/ejc/article.cgi?issn=03432521&issue=v52i0003&article=223_dvousisaoaua

http://journals.ohiolink.edu/ejc/article.cgi?issn=03432521&issue=v52i0003&article=223_dvousisaoaua


Ecological Cost-Benefit Modelling of Herbivore Habitat Quality Degradation due to Range Fragmentation.

Lundqvist, Henrik. Transactions in GIS vol. 11 issue 5 October 2007. p. 745-763

Fragmentation of grazing ranges and ensuing rise in edge effects decrease forage range quality for large herbivores. A

method is proposed to quantify, in ecological cost-benefit terms, the negative impact of fragmentation by linear

structures with special emphasis on summer ranges of semi-domesticated reindeer ( Rangifer t. tarandus).

The method is also applicable to other terrestrial species and on different scales. The term ‘reachability’ is introduced for this measurement, which integrates forage quality, quantity and

availability, as well as the costs of the animal's movement in a variable landscape and across fragmenting linear structures.

The method uses a cost-distance algorithm, commonly available in GIS software. Effective distances and reachability

over large areas are calculated from evenly distributed sample points.

Effects of varying sample point distance, fragmenting structure friction weight and density, and edge effect depth were

analysed for model calibration. In an example the model was used for estimation of reachability alteration due to linear

structures in the summer ranges of the Handölsdalen reindeer herding district in Sweden, where hourly GPS positions of 10

free-ranging female reindeer were available.

In these data the reindeer population density appeared to decrease up to 1 km away from roads, but no effect from hiking trails was detected. The reachability model quantified a loss of

2.2–2.7% in range quality due to range fragmentation.

http://journals.ohiolink.edu/ejc/article.cgi?issn=13611682&issue=v11i0005&article=745_ecmohhqddtrf

http://journals.ohiolink.edu/ejc/article.cgi?issn=13611682&issue=v11i0005&article=745_ecmohhqddtrf


Landscape-based geostatistics: a case study of the distribution of blue crab in Chesapeake Bay.

Jensen, Olaf P.; Christman, Mary C.; Miller, Thomas J. Environmetrics vol. 17 issue 6 September 2006. p. 605 - 621

Geostatistical techniques have gained widespread use in ecology and environmental science. Variograms are commonly used to describe and examine spatial autocorrelation, and kriging has

become the method of choice for interpolating spatially-autocorrelated variables. To date, most applications of geostatistics have defined the separation between sample points using simple

Euclidean distance. In heterogeneous environments, however, certain landscape features may act as absolute or semi-permeable

barriers.

This effective separation may be more accurately described by a measure of distance that accounts for the presence of barriers. Here we present an approach to geostatistics based on a lowest-cost path (LCP) function, in which the cost of a path is a function of both the

distance and the type of terrain crossed.

The modified technique is applied to 13 years of survey data on blue crab abundance in Chesapeake Bay. Use of this landscape-based

distance metric significantly changed estimates of all three variogram parameters. In this case study, although local differences in kriging predictions were apparent, the use of the landscape-based distance metric did not result in consistent improvements in kriging

accuracy.



Effect of depression storage capacity on overland-flow generation for rough horizontal surfaces: water transfer distance and

scaling.Darboux, F.; Davy, P.; Gascuel-Odoux, C.

Earth Surface Processes and Landforms vol. 27 issue 2 February 2002. p. 177 - 191

Overland-flow triggering on rough surfaces was investigated using an understanding-oriented model.

The model was based on conditioned-walker technique and developed to simulate and analyse the evolution of puddle connection on numerically generated rough surfaces. The

percolation theory gave a theoretical framework to formalize model outputs and to study overland-flow scaling. Overland-flow triggering appeared consistent with a percolation process.

A scale-change exponent was suggested. New insights based on the concept of transfer distance of water were emphasized.

Transfer distance enabled us to analyse the water redistribution inside a field and helped to define rainfall efficiency when

infiltration occurred.



Uncertainties in real-time flood forecasting with neural networks.

Han, Dawei; Kwong, Terence; Li, Simon. Hydrological Processes vol. 21 issue 2 15 January 2007. p. 223 - 228

Although artificial neural networks (ANNs) have been applied in rainfall runoff modelling for many years, there are still many important issues unsolved that have prevented this powerful non-linear tool from wide

applications in operational flood forecasting activities.

This paper describes three ANN configurations and it is found that a dedicated ANN for each lead-time step has the best performance and a multiple output form has the worst result. The most popular form

with multiple inputs and single output has the average performance. In comparison with a linear transfer function (TF) model, it is found that ANN models are uncompetitive against the TF model in short-

range predictions and should not be used in operational flood forecasting owing to their complicated calibration process. For longer range predictions, ANN models have an improved chance to perform better than the TF model; however, this is highly dependent on the training data arrangement and there are undesirable uncertainties

involved, as demonstrated by bootstrap analysis in the study.

To tackle the uncertainty issue, two novel approaches are proposed: distance analysis and response analysis. Instead of discarding the

training data after the model’s calibration, the data should be retained as an integral part of the model during its prediction stage and the

uncertainty for each prediction could be judged in real time by measuring the distances against the training data.

The response analysis is based on an extension of the traditional unit hydrograph concept and has a very useful potential to reveal the hydrological characteristics of ANN models, hence improving user

confidence in using them in real time.


Diunduh dari:

Encyclopedia of EnvironmetricsVolume 1

Abdel H. El-Shaarawi, Walter W. PiegorschWiley, Dec 31, 2001 - 2672 pages

Environmetrics covers the development and application of quantitative methods in the environmental sciences.

It provides essential tools for understanding, predicting, and controlling the impacts of agents, both man-made and

natural, which affect the environment.

Basic and applied research in this area covers a broad range of topics.

Primary among these are the quantitative sciences, such as statistics, probability and applied mathematics,

chemometrics, and econometrics.

Applications are also important, for example in, ecology and environmental biology, public health, atmospheric science, geology, engineering, risk management, and

regulatory/governmental policy amongst others.

Diunduh dari:

G. P. Patil and C. R. Rao, eds., Handbook of Statistics, Vol. 12© 1994 ElsevierScienceB.V. All rights reserved.Environmetrics: An Emerging Science

(J. Stuart Hunter)

Environmetrics finds its origins in the search for the understanding of the natural phenomena that surrounds

mankind. In antiquity these studies led to the creation of the earliest instruments of measurement and to the beginning arts of

mathematical description.

Today's environmental studies combine the modern tools of physics and chemistry with mathematical modeling of

great sophistication.

But beyond measurement and mathematics, environmetrics has become a unique 'n-science', a meeting

ground for the ecologist, the natural and social scientist, the engineer and statistician, and ultimately the political

scientist.

….. dst………. environmetrika

Diunduh dari: smno.kampus.ub.agst2012

Dihimpun dan diabstraksikan: Smno.psl-ppsub.agst2012 ENVIRONMETRIKA.

Documents

environmetrics environmetrics

environmental engineering

environmental monitoring

recent environmental

official journal

multidisciplinary journal

quantitative disciplines

diunduh dari