Applying the technique of image classification to climate science: the case of Andalusia (Spain)

This paper proposes an empirical climate classification method based on the application of multivariate statistics. In this method, the technique of supervised and unsupervised image classification is used to classify the data and define climatic units. envi software is used to perform the image classification, specifically, the Iterative Self‐Organizing Data Analysis Technique algorithm. Supervised classification is also applied based on reference variables, fundamental parameters and a classifier. The obtained results display greater objectivity, reliability, operability, accessibility and reproducibility than previous climate classifications devised for the region of Andalusia (Spain), taking into account that these previous classifications were not based on quantitative criteria.     

Time Averages,Climatic Change,and Predictability

Traditional averaging procedures (e.g., annual average, climatic normals) are shown to have both theoretical and practical failings when used for prediction or for detection of small climatic changes. Transformation of a multivariate autoregressive process (predictable components analysis) provides a useful way to construct empirical functions capturing the dynamic behavior of climatic variables.     

Climatic signal in tree-ring chronologies of Cedrus deodara from Chitral Hindukush Range of Pakistan

Tree-rings are an important tool for the investigation of paleoclimatic records for regions or periods of time with no instrumental climatic data. However, the responses of different species and sites to various climatic parameters are unusual. In the present study, we developed tree-ring-width chronologies of Cedrus deodara from three different sites of Chitral Hindukush range of Pakistan. The study was conducted to understand tree-growth climate relationship and its applicability in proxy climate investigations. The chronologies covered the past 469 to 595 years, with a mean segment length (MSL) ranging from 148 to 223 years. Climatic data obtained from the three weather stations showed strong correlation and was found useful for tree-ring climate relationships. Correlation Function (CF) and Response Function (RF) analysis showed that spring precipitation (March–May) is a critical limiting factor for tree-ring growth, and temperature prior to November may also play a major role in affecting tree ring-growth. The results exposed that the three sites have continuous relationship indicated that only single species from different locations are affected by the same environmental variables and hence can be used in climate reconstruction in combination. The Cedrus deodara chronologies developed at different locations had several corresponding narrow and wide marker rings indicating a large macroclimatic response to regional climatic conditions. The current study suggests that the tree-rings of Cedrus deodara from the Chitral Hindukush range could be used to develop chronologies for the reconstruction of seasonal climatic variables.     

Using event-history analysis to examine the causes of semi-sedentism among shifting cultivators: a case study of the Haudenosaunee,AD 1500–1700

Event-history analysis is often used in the social sciences to study the occurrence of particular events over the lifespan of individuals and the impact of various factors on the rate at which those events occur. Like individuals, settlements can be analyzed and important events, such as founding or abandonment, can be studied using this method. Thus, as Richard Paine (1992) has noted, the technique can be useful in archaeological investigations of settlement processes. In this research we use it to explore the causes of settlement abandonment among a temperate shifting cultivators in an attempt to better understand the ecology of this adaptation and in order to evaluate the merits of the method. The sixteenth- and seventeenth-century Haudenosaunee (Iroquois) of northeastern North America present an interesting case study for applying event-history analysis to archaeological settlement dynamics because of the wealth of archaeological settlement data and detailed historic record that allows us to parse out historical factors and analyze the remaining ecological factors. We use event-history analysis as an alternative means for evaluating the relative and absolute effects of several variables that may have been predictive of the lifespan of settlements and the timing of their removal. The results suggest that the decision to move from a village was a complex process in which the population size of a village may have been the single most important, but not the only, determinant of settlement duration.     

Evolution of Expenditure in the Budget of the European Union (1957–2002)

This article analyses the evolution of Community expenditure, on the basis of the data given in the budget and in the EDF, from the origin of the process in 1957 until the year 2002, the last definitive figures. The technique of principal component factor analysis has been applied to these variables. The basic objective of this study is to detect the interrelationships among the policies of the Union and to effect a classification of them, in order to detect the priorities of the European project and to estimate the dimension of the impact of its policies during the period.     

Geographically Weighted Discriminant Analysis

In this article, we propose a novel analysis technique for geographical data, Geographically Weighted Discriminant Analysis. This approach adapts the method of Geographically Weighted Regression (GWR), allowing the modeling and prediction of categorical response variables. As with GWR, the relationship between predictor and response variables may alter over space, and calibration is achieved using a moving kernel window approach. The methodology is outlined and is illustrated with an example analysis of voting patterns in the 2005 UK general election. The example shows that similar social conditions can lead to different voting outcomes in different parts of England and Wales. Also discussed are techniques for visualizing the results of the analysis and methods for choosing the extent of the moving kernel window.     

Comparative Spatial Filtering in Regression Analysis

One approach to dealing with spatial autocorrelation in regression analysis involves the filtering of variables in order to separate spatial effects from the variables’ total effects. In this paper we compare two filtering approaches, both of which allow spatial statistical analysts to use conventional linear regression models. Getis’ filtering approach is based on the autocorrelation observed with the use of the G_i local statistic. Griffith's approach uses an eigenfunction decomposition based on the geographic connectivity matrix used to compute a Moran's I statistic. Economic data are used to compare the workings of the two approaches. A final comparison with an autoregressive model strengthens the conclusion that both techniques are effective filtering devices, and that they yield similar regression models. We do note, however, that each technique should be used in its appropriate context.     

Multicollinearity and Parameter Estimation in Simultaneous-Equation Models of Fluvial Systems

Simultaneous-equation statistical models are an attractive method for directly analyzing interactions among components of geomorphic systems. This study demonstrates that the utility of simultaneous-equation analysis is limited for fluvial systems by inherent multicollinearity among hydrologic and morphologic variables. Although multicollinearity for observed data may not be severe, estimation procedures for simultaneous-equation models often enhance this multicollinearity to problematic levels. Diagnostic tests are applied to three models of fluvial systems to illustrate the severity of the problem. It is recommended that investigators who develop simultaneous-equation models perform appropriate diagnostic evaluations to determine the impact of multicollinearity on specific parameter estimates.     

A QUANTITATIVE FABRIC ANALYSIS APPROACH TO THE DISCRIMINATION OF WHITE MARBLES*

Quantitative fabric analysis was applied in order to discriminate better among white marbles from various quarries of archaeological interest. This method provides an effective complementary tool to a characterization based upon petrography, cathodoluminescence microscopy and stable isotopes. Very good discrimination of marbles is achieved with the help of simple variables such as major axis and the shape-specific PARlS-factor. Using quantitative fabric analysis, marbles with similar cathodomicrofacies, as, for example, the Naxian quarries of Apiranthos, Koronos, Flerio and Kinidaros and the quarry of St. Beat (French Pyrenees), can be distinguished from each other. Marbles collected within one quarry may display dissimilar cathodomicrofacies. The common origin of such specimens can be determined with the aid of quantitative fabric analysis, as shown for the quarries of Kinidaros as well as St. Béat.     

Migration and Changing Employment Status: A Hazard Function Analysis

The effects of different employment-status transitions on migration choices are considered from a search-theoretic perspective. A discrete-time hazard function for migration decisions is estimated on data for young males of rural origin in France. Employment-status transitions are handled as endogenous time-varying covariates. The model is estimated by distance of move. The results show that the long-distance migration hazard is significantly related to labor market variables, and, ceteris paribus, is highest among job-gainers compared to the other transition groups. The probability of contracted (long-distance) migration is found to be higher than that of speculative migration for unemployed workers, especially those who are low-educated. Evidence consistent with cumulative inertia is found for long-distance moves. Short-distance migration hazards are found to be unrelated to labor market variables (including employment-status transitions) and to display no systematic pattern of duration dependence.     

A Local Model for Multivariate Analysis: Extending Wartenberg’s Multivariate Spatial Correlation

Local analysis can provide specific information about individual observations that is often useful in understanding nonstationary interactions among variables. This paper extends the application of Wartenberg’s Multivariate Spatial Correlation (MSC) method to a local setting. The original MSC can be considered as an adaptation of Principal Component Analysis for spatial effects with respect to spatial autocorrelation. The extended MSC method described in this paper, however, further incorporates another spatial effect, spatial heterogeneity, by the addition of geographic weights in standardizing the data and in calculating the spatial association weight matrix. The extension allows more local analysis and facilitates additional visualization of the results. The geographically weighted MSC is illustrated and justified using the classic dataset collected by André-Michel Guerry on moral statistics in 1830s France.     

Modeling Categorical Data with Chi Square Automatic Interaction Detection and Correspondence Analysis

For the past decade we have been concerned with the application of categorical data techniques to mobility and housing choice. In a previous issue of this journal we reviewed a number of these modeling techniques. We now extend that earlier work by introducing correspondence analysis as a geometric interpretative technique that fits in an intermediate position between CHAID and nested logit analysis. The method is illustrated on the same housing and tenure choice data as was used in the previous paper.     

Field data validation of an algorithm for computing obsidian effective hydration temperature

This paper describes an analysis to validate the effective hydration temperature (EHT) algorithm for obsidian [Rogers, A.K., 2007. Effective hydration temperature of obsidian: a diffusion-theory analysis of time-dependent hydration rates. J. Arch. Sci. 34, 656-665], using hourly temperature data from the Amargosa Desert Research Site near Beatty, NV. These data were used as input to a numerical model of the temperature-dependent diffusion process, and EHT was calculated yearly and for the aggregate. The same temperature data were processed to extract input parameters for the climatic model reported and used as input for EHT computation. EHT as computed from recorded hourly data was found to be within 1 °C of that computed from the climatic model. It is also shown that computed EHT differences between sites are not sensitive to whether air or surface temperature data are used, as long as they are used consistently; however, surface temperature data must be used if depth corrections are to be made.     

New Methods of Census Record Linking

The Minnesota Population Center (MPC) has released linked datasets through its NAPP and IPUMS projects, making them readily accessible to researchers. Prior to the availability of complete count census microdata from the MPC, researchers applied various forms of record-linking software. This essay describes the techniques used in the MPC's linking program and briefly compares this technique with those used by other researchers. The key feature of the MPC linking method is the construction of cumulative name similarity scores, based on approximately 2.5 billion record comparisons; we also use support vector mechanics to classify potential links. This article explains modifications made for the final linked datasets and includes a discussion of the role of weighting variables when using linked data.     

Using Spatial Filters and Exploratory Data Analysis to Enhance Regression Models of Spatial Data

Residual spatial autocorrelation is a situation frequently encountered in regression analysis of spatial data. The statistical problems arising due to this phenomenon are well‐understood. Original developments in the field of statistical analysis of spatial data were meant to detect spatial pattern, in order to assess whether corrective measures were required. An early development was the use of residual autocorrelation as an exploratory tool to improve regression analysis of spatial data. In this note, we propose the use of spatial filtering and exploratory data analysis as a way to identify omitted but potentially relevant independent variables. We use an example of blood donation patterns in Toronto, Canada, to demonstrate the proposed approach. In particular, we show how an initial filter used to rectify autocorrelation problems can be progressively replaced by substantive variables. In the present case, the variables so retrieved reveal the impact of urban form, travel habits, and demographic and socio‐economic attributes on donation rates. The approach is particularly appealing for model formulations that do not easily accommodate positive spatial autocorrelation, but should be of interest as well for the case of continuous variables in linear regression.     

A Wavelet‐Based Extension of Generalized Linear Models to Remove the Effect of Spatial Autocorrelation. 基于小波扩展广义线性模型消除空间自相关的影响

Biogeographical studies are often based on a statistical analysis of data sampled in a spatial context. However, in many cases standard analyses such as regression models violate the assumption of independently and identically distributed errors. In this article, we show that the theory of wavelets provides a method to remove autocorrelation in generalized linear models (GLMs). Autocorrelation can be described by smooth wavelet coefficients at small scales. Therefore, data can be decomposed into uncorrelated and correlated parts. Using an appropriate linear transformation, we are able to extend GLMs to autocorrelated data. We illustrate our new method, called the wavelet‐revised model (WRM), by applying it to multiple regression with response variables conforming to various distributions. Results are presented for simulated data and real biogeographical data (species counts of the plant genus Utricularia [bladderworts] in grid cells throughout Germany). The results of our WRM are compared with those of GLMs and models based on generalized estimating equations. We recommend WRMs, especially as a method that allows for spatial nonstationarity. The technique developed for lattice data is applicable without any prior knowledge of the real autocorrelation structure.     

Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity

Spatial nonstationarity is a condition in which a simple “global” model cannot explain the relationships between some sets of variables. The nature of the model must alter over space to reflect the structure within the data. In this paper, a technique is developed, termed geographically weighted regression, which attempts to capture this variation by calibrating a multiple regression model which allows different relationships to exist at different points in space. This technique is loosely based on kernel regression. The method itself is introduced and related issues such as the choice of a spatial weighting function are discussed. Following this, a series of related statistical tests are considered which can be described generally as tests for spatial nonstationarity. Using Monte Carlo methods, techniques are proposed for investigating the null hypothesis that the data may be described by a global model rather than a non-stationary one and also for testing whether individual regression coefficients are stable over geographic space. These techniques are demonstrated on a data set from the 1991 U.K. census relating car ownership rates to social class and male unemployment. The paper concludes by discussing ways in which the technique can be extended.     

Paleoenvironmental reconstruction at Canyon del Muerto,Arizona, based on principal-component analysis

A multivariate statistical technique, principal-component analysis, is used to interpret pollen assemblages from archaeological context in terms of paleoenvironmental information. The pollen samples originate from an archaeological site in northeastern Arizona (Canyon del Muerto) covering the period between AD 700 and AD 1300. Through the use of principal-component analysis the percentage constraint in the pollen counts is removed and the data set effectively reduced to groups of co-varying taxa. Once these groups are ecologically defined as to the environment they represent, their changes of dominance through time can be analysed. This study has shown a correlation between a population expansion in Canyon del Muerto (AD 1050–1150) and the dominance of upland forest types suggesting slightly cooler and/or wetter conditions. The pollen data compare well with the tree-ring indices for this region. Local disturbance is reflected in the record during the period of greatest population. A shift to a shrubland vegetation during the peak construction phase indicates the clearing of cottonwood, fir, spruce and pine (all found within the site) by local inhabitants. Thus, the palynological evidence suggests both cultural and climatic factors are involved in the explanation of pollen deposition.     

Amplitudes of orbitally induced climatic cycles and patterns of hominin speciation

Palaeoanthropologists and archaeologists have long invoked climate change to explain aspects of human evolution. Collection of new climatic and environmental data combined with new fossil discoveries and methodological improvements continue to make exploration of this link a vital endeavour in studying human evolution. The current study employs a global climatic dataset and a rigorously compiled catalogue of hominin first and last appearance dates to test the effects of changes in temperature on hominin speciation and extinction. Through the use of wavelet analysis and bandpass filters the eccentricity, obliquity, and precession components of the studied climatic record are extracted and tested independently for associations with patterns of speciation and extinction. Results suggest that all three components may play a role in speciation events, but that only the obliquity cycle shows a statistically significant relationship with extinction events. It is suggested that, whilst climatic factors could contribute to the appearance of new hominin species, subsequent competition between these species may lead to their extinction.     

THE TOURISM CLIMATIC INDEX: A METHOD OF EVALUATING WORLD CLIMATES FOR TOURISM

In this essay a method of computing tourism climatic indices (TCIS) is described. These indices represent a quantitative evaluation of world climate for the purposes of international tourism. A series of rating systems is developed to provide a systematic basis for assessing the climatic elements that most affect the quality of the tour- ism experience. The problem of weighting climatic variables in the TCI formula is also discussed. Monthly TCIS have been computed for 453 meteorological stations throughout the world, and the results have been generalized in 12 monthly world maps.
L' article offre une méthode pour calculer des indices climatoogiques touristiques (ICT), qui représentent une évaluation quantitative des climats mondiaux, destinée aux besoins du tourisme international. On développe une série de systèmes d' évaluation d' éléments climatologiques, fournissant ainsi une base systématique pour évaluer lesquels de ces derniers influencent le plus la qualityé de l' expérience touristique vécu. L'article souléve aussi les problhes réliés aux valeurs relatives, soient les poids, des variables qui entrent dans la formule de l' ICT. Des valeurs mensuelles ont été compilées pour 453 stations météorologiques à travers le monde, et les résultats sont présentés, en forme généralisée sur une base mensuelle, dans douze cartes mondiales.