Spatial Autoregressive Models for Geographically Hierarchical Data Structures

This article discusses how standard spatial autoregressive models and their estimation can be extended to accommodate geographically hierarchical data structures. Whereas standard spatial econometric models normally operate at a single geographical scale, many geographical data sets are hierarchical in nature—for example, information about houses nested into data about the census tracts in which those houses are found. Here we outline four model specifications by combining different formulations of the spatial weight matrix W and of ways of modeling regional effects. These are (1) groupwise W and fixed regional effects; (2) groupwise W and random regional effects; (3) proximity‐based W and fixed regional effects; and (4) proximity‐based W and random regional effects. We discuss each of these model specifications and their associated estimation methods, giving particular attention to the fourth. We describe this as a hierarchical spatial autoregressive model. We view it as having the most potential to extend spatial econometrics to accommodate geographically hierarchical data structures and as offering the greatest coming together of spatial econometric and multilevel modeling approaches. Subsequently, we provide Bayesian Markov Chain Monte Carlo algorithms for implementing the model. We demonstrate its application using a two‐level land price data set where land parcels nest into districts in Beijing, China, finding significant spatial dependence at both the land parcel level and the district level.     

Closed‐Form Maximum Likelihood Estimates of Nearest Neighbor Spatial Dependence

Models of n² potential spatial dependencies among n observations spread irregularly over space seem unlikely to yield simple structure. However, the use of the nearest neighbor leads to a very parsimonious eigenstructure of the associated adjacency matrix which results in an extremely simple closed form for the log determinant. In turn, this leads to a closed‐form solution for the maximum likelihood estimates of the spatially autoregressive and mixed regressive spatially autoregressive models. With the closed‐form solution, one can find the neighbors and compute maximum likelihood estimates for 100,000 observations in under one minute. The model has theoretical, pedagogical, diagnostic, modeling, and methodological applications. For example, the model could serve as a more enlightened null hypothesis for geographic data than spatial independence.     

Quick Computation of Spatial Autoregressive Estimators

Spatial estimators usually require the manipulation of n² relations among n observations and use operations such as determinants, eigenvalues, and inverses whose operation counts grow at a rate proportional to n³. This paper provides ways to quickly compute estimates when the dependent variable follows a spatial autoregressive process, which by appropriate specification of the independent variables can subsume the case when the errors follow a spatial autoregressive process. Since only nearby observations tend to affect a given observation, most observations have no effect and hence the spatial weight matrix becomes sparse. By exploiting sparsity and rearranging computations, one can compute estimates at low cost. As a demonstration of the efficacy of these techniques, the paper provides a Monte Carlo study whereby 3,107 observation regressions require only 0.1 seconds each when using Matlab on a 200 Mhz Pentium Pro personal computer. In addition, the paper illustrates these techniques by examining voting behavior across U.S. counties in the 1980 presidential election.     

An Introduction to the Network Weight Matrix

This study introduces the network weight matrix as a replacement for the spatial weight matrix to measure the spatial dependence between links of a network. This matrix stems from the concepts of betweenness centrality and vulnerability in network science. The elements of the matrix are a function not simply of proximity, but of network topology, network structure, and demand configuration. The network weight matrix has distinctive characteristics, which are capable of reflecting spatial dependence between traffic links: (1) elements are allowed to have negative and positive values capturing the competitive and complementary nature of links, (2) diagonal elements are not fixed to zero, which takes the self‐dependence of a link upon itself into consideration, and (3) elements not only reflect the spatial dependence based on the network structure, but they acknowledge the demand configuration as well. We verify the network weight matrix by modeling traffic flows in a 3 × 3 grid test network with 9 nodes and 24 directed links connecting 72 origin‐destination (OD) pairs. Models encompassing the network weight matrix outperform both models without spatial components and models with the spatial weight matrix. The network weight matrix represents a more accurate and defensible spatial dependency between traffic links, and offers the potential to augment traffic flow prediction.     

Application of LASSO to the Eigenvector Selection Problem in Eigenvector‐based Spatial Filtering

Eigenvector‐based spatial filtering is one of the often used approaches to model spatial autocorrelation among the observations or errors in a regression model. In this approach, a subset of eigenvectors extracted from a modified spatial weight matrix is added to the model as explanatory variables. The subset is typically specified via the selection procedure of the forward stepwise model, but it is disappointingly slow when the observations n take a large number. Hence, as a complement or alternative, the present article proposes the use of the least absolute shrinkage and selection operator (LASSO) to select the eigenvectors. The LASSO model selection procedure was applied to the well‐known Boston housing data set and simulation data set, and its performance was compared with the stepwise procedure. The obtained results suggest that the LASSO procedure is fairly fast compared with the stepwise procedure, and can select eigenvectors effectively even if the data set is relatively large (n = 10⁴), to which the forward stepwise procedure is not easy to apply.     

Model Uncertainty in Matrix Exponential Spatial Growth Regression Models

This article considers the most important aspects of model uncertainty for spatial regression models, namely, the appropriate spatial weight matrix to be employed and the appropriate explanatory variables. We focus on the spatial Durbin model (SDM) specification in this study that nests most models used in the regional growth literature, and develop a simple Bayesian model‐averaging approach that provides a unified and formal treatment of these aspects of model uncertainty for SDM growth models. The approach expands on previous work by reducing the computational costs through the use of Bayesian information criterion model weights and a matrix exponential specification of the SDM model. The spatial Durbin matrix exponential model has theoretical and computational advantages over the spatial autoregressive specification due to the ease of inversion, differentiation, and integration of the matrix exponential. In particular, the matrix exponential has a simple matrix determinant that vanishes for the case of a spatial weight matrix with a trace of zero. This allows for a larger domain of spatial growth regression models to be analyzed with this approach, including models based on different classes of spatial weight matrices. The working of the approach is illustrated for the case of 32 potential determinants and three classes of spatial weight matrices (contiguity‐based, k‐nearest neighbor, and distance‐based spatial weight matrices), using a data set of income per capita growth for 273 European regions.     

DETERMINANTS OF KNOWLEDGE PRODUCTION AND THEIR EFFECTS ON REGIONAL ECONOMIC GROWTH

ABSTRACT We provide a Bayesian spatial Markov Chain Monte Carlo model composition (MC³) analysis of growth rates in European regional patenting activity. Based on theoretical models on innovation and growth, we identify a large set of candidate explanatory variables that characterize regional stocks of knowledge, including: human resources devoted to innovative activity, scientific and technical capabilities, public and private investments, government policies, as well as regional industry structure, and indicators of regional technology gaps that reflect distance from the technological frontier. Our analysis shows that accommodating spatial dependence and heterogeneity leads to different conclusions regarding factors important for technological transfer and knowledge spillovers.     

A SPATIAL AND TEMPORAL AUTOREGRESSIVE LOCAL ESTIMATION FOR THE PARIS HOUSING MARKET

ABSTRACT This original study examines the potential of a spatiotemporal autoregressive Local (LSTAR) approach in modeling transaction prices for the housing market in inner Paris. We use a data set from the Paris Region notary office (Chambre des notaires d’Île‐de‐France) which consists of approximately 250,000 transactions units between the first quarter of 1990 and the end of 2005. We use the exact X–Y coordinates and transaction date to spatially and temporally sort each transaction. We first choose to use the STAR approach proposed by Pace et al., 1998 . This method incorporates a spatiotemporal filtering process into the conventional hedonic function and attempts to correct for spatial and temporal correlative effects. We find significant estimates of spatial dependence effects. Moreover, using an original methodology, we find evidence of a strong presence of both spatial and temporal heterogeneity in the model. It suggests that spatial and temporal drifts in households socio‐economic profiles and local housing market structure effects are certainly major determinants of the price level for the Paris Housing Market.     

Designs for Detecting Spatial Dependence

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.     

Local Forms of Spatial Analysis

Local forms of spatial analysis focus on exceptions to the general trends represented by more traditional global forms of spatial analysis. There is currently a rapid expansion in the development of such techniques but their history almost exactly parallels that of Geographical Analysis, with the first examples of local analysis appearing in the late 1960s. Indeed, Geographical Analysis has published many of the significant contributions in this field. This paper reviews the development of local forms of spatial analysis and assesses the current situation. Following a discussion on the nature and importance of local analysis, examples are given of local forms of point pattern analysis; local graphical approaches; local measures of spatial dependency; the spatial expansion method; adaptive filtering; multilevel modeling; geographically weighted regression; random coefficients models; autoregressive models; and local forms of spatial interaction models.     

INTERPRETING SPATIAL ECONOMETRIC ORIGIN‐DESTINATION FLOW MODELS

Spatial interaction or gravity models have been used to model flows that take many forms, for example population migration, commodity flows, traffic flows, all of which reflect movements between origin and destination regions. We focus on how to interpret estimates from spatial autoregressive extensions to the conventional regression‐based gravity models that relax the assumption of independence between flows. These models proposed by LeSage and Pace ( 2008 , 2009 ) define spatial dependence involving flows between regions. We show how to calculate partial derivative expressions for these models that can be used to quantify these various types of effect that arise from changes in the characteristics/explanatory variables of the model.     

THE OPTIMAL LOCATIONS OF MULTIPLE BRIDGES,CONNECTING FACILITIES,OR PRODUCT VARIETIES*

ABSTRACT This paper considers the optimal locations of two or more facilities, and the optimal number of facilities, when trips are made in pairs. The results are the same as standard models of spatial competition when there is perfect matching, but not when there is random matching. The first interpretation is bridges across a river, with residential locations on one side matched perfectly or randomly to jobs on the other side. The second interpretation is connecting facilities, such as tennis courts or restaurants where pairs of consumers meet. The third interpretation is product differentiation, with husbands and wives jointly choosing from among varieties.     

Developing Spatial Weight Matrices for Incorporation into Multiple Linear Regression Models: An Example Using Grizzly Bear Body Size and Environmental Predictor Variables

In this study, we develop spatial autoregressive (SAR) models relating grizzly bear body length to environmental predictor variables in the Alberta Rocky Mountains. We examine the ability of several different spatial neighborhoods to model spatial dependence and compare the estimated parameters and residuals from a standard linear regression model (LRM) with those from three types of SAR models: error, lag, and Durbin. Further, we examine variable selection in the presence of negative dependence by repeating the modeling process using a SAR model. Two findings are that significant negative spatial dependence was present in the residuals of the LRM and that the choice of spatial neighborhood greatly affects the ability to detect spatial dependence. The incorporation of appropriate spatial weights into SAR models improves the fit and increases the significance of the parameter estimates vis‐à‐vis the linear model. The results of this study indicate that negative dependence may not have as severe negative effects on variable selection and parameter estimation as positive dependence. An examination of spatial dependence in regression modeling appears to be an important means of exploring the appropriateness of a sampling framework, predictor variables, and model form. En este estudio desarrollamos modelos espaciales autorregresivos (SAR) que vinculan la longitud del cuerpo de osos grizzli con variables predictivas ambientales en las montañas rocosas de Alberta, Canadá. Examinamos la capacidad de varias vecindades espaciales para modelar la dependencia espacial y la comparación de los parámetros estimados, así como los residuos de un modelo de regresión lineal estándar (LRM) versus tres tipos de modelos SAR: error, retraso (lag) y Durbin. Además, se examina la selección de variables en la presencia de dependencia negativa mediante la repetición del proceso de modelado con un modelo de SAR. El estudio concluye que: 1) existe dependencia espacial negativa significativa en los residuos de la LRM y; 2) la selección de la vecindad espacial afecta en gran medida la capacidad de detectar la dependencia espacial. La incorporación de ponderaciones espaciales correspondientes a los modelos SAR mejora el ajuste y aumenta la importancia de los parámetros estimados versus el modelo lineal. Los resultados de este estudio indican que la dependencia negativa puede no tener los graves efectos negativos en la selección de variables y la estimación de parámetros si se comparan dichos efectos con = la dependencia positiva. Los autores recomiendan un examen de la dependencia espacial en modelos de regresión como medio importante para explorar la conveniencia de un marco de muestreo, de variables de predicción, y de la forma del modelo. 本文构建了阿尔伯达省落基山脉地区的灰熊体态大小与环境预测变量之间的空间自回归模型（SAR）,检验了几种以不同空间邻域矩阵拟合变量的空间相关性,并比较了标准回归模型(LRM)与几种不同类型的SAR模型（空间残差模型、空间滞后模型和空间杜宾模型）的估计参数和残差大小。进而利用一种SAR模型重复模拟过程,进一步测试变量选择对负相关性存在的影响。研究表明,显著的空间负相关存在于LRM的残差中,且空间邻域权重的选择很大程度上影响模型空间相关性的探测能力。将适当的空间权重引入SAR模型中可提高拟合精度,增加相对于线性模型参数估计的显著性。研究结果表明,负相关性在变量选择和参数估计上严重负影响的程度不如正相关性强。回归模型中空间相关性检验似乎是采样结构、预测变量和模型形式适用性分析的一个重要途径。     

A Spatial Prior for Bayesian Vector Autoregressive Models

In this paper we develop a Bayesian prior motivated by cross-sectional spatial autoregressive models for use in time-series vector autoregressive forecasting involving spatial variables. We compare forecast accuracy of the proposed spatial prior to that from a vector autoregressive model relying on the Minnesota prior and find a significant improvement. In addition to a spatially motivated prior variance as in LeSage and Pan (1995) we develop a set of prior means based on spatial contiguity. A Theil-Goldberger estimator may be used for the proposed model making it easy to implement.     

Comparison of Moran's I and Geary's c in Multivariate Spatial Pattern Analysis

This article compares multivariate spatial analysis methods that include not only multivariate covariance, but also spatial dependence of the data explicitly and simultaneously in model design by extending two univariate autocorrelation measures, namely Moran's I and Geary's c. The results derived from the simulation datasets indicate that the standard Moran component analysis is preferable to Geary component analysis as a tool for summarizing multivariate spatial structures. However, the generalized Geary principal component analysis developed in this study by adding variance into the optimization criterion and solved as a trace ratio optimization problem performs as well as, if not better than its counterpart the Moran principal component analysis does. With respect to the sensitivity in detecting subtle spatial structures, the choice of the appropriate tool is dependent on the correlation and variance of the spatial multivariate data. Finally, the four techniques are applied to the Social Determinants of Health dataset to analyze its multivariate spatial pattern. The two generalized methods detect more urban areas and higher autocorrelation structures than the other two standard methods, and provide more obvious contrast between urban and rural areas due to the large variance of the spatial component.     

A Geostatistical Linear Regression Model for Small Area Data. 一种适用于小区域数据的地统计线性回归模型

We present a new linear regression model for use with aggregated, small area data that are spatially autocorrelated. Because these data are aggregates of individual‐level data, we choose to model the spatial autocorrelation using a geostatistical model specified at the scale of the individual. The autocovariance of observed small area data is determined via the natural aggregation over the population. Unlike lattice‐based autoregressive approaches, the geostatistical approach is invariant to the scale of data aggregation. We establish that this geostatistical approach also is a valid autoregressive model; thus, we call this approach the geostatistical autoregressive (GAR) model. An asymptotically consistent and efficient maximum likelihood estimator is derived for the GAR model. Finite sample evidence from simulation experiments demonstrates the relative efficiency properties of the GAR model. Furthermore, while aggregation results in less efficient estimates than disaggregated data, the GAR model provides the most efficient estimates from the data that are available. These results suggest that the GAR model should be considered as part of a spatial analyst's toolbox when aggregated, small area data are analyzed. More important, we believe that the GAR model's attention to the individual‐level scale allows for a more flexible and theory‐informed specification than the existing autoregressive approaches based on an area‐level spatial weights matrix. Because many spatial process models, both in geography and in other disciplines, are specified at the individual level, we hope that the GAR covariance specification will provide a vehicle for a better informed and more interdisciplinary use of spatial regression models with area‐aggregated data.     

The Assessment of Spatial Autocorrelation through Constrained Multiple Regression

Most published measures of spatial autocorrelation (SA) can be recast as a (normalized) cross-product statistic that indexes the degree of relationship between corresponding entries from two matrices—one specifying the spatial connections among a set of n locations, and the other reflecting a very explicit definition of similarity between the set of values on some variable x realized over the n locations. We first give a very brief sketch of the basic cross-product approach to the evaluation of SA, and then generalize this strategy to include less restrictive specifications for the notion of similarity between the values on x. Using constrained multiple regression, the characterization of variate similarity basic to any assessment of SA can itself be framed according to the information present in the measure of spatial separation. These extensions obviate the inherent arbitrariness in how SA is usually evaluated, which now results from the requirement of a very restrictive definition of variate similarity before a cross-product index can be obtained.     

Isotopic anthropology of rural German medieval diet: intra- and inter-population variability

This study investigates the diet of an eleventh century CE parish community located in northwestern Germany. We assessed the isotopic compositions of human (n = 24) and faunal (n = 17) bone collagen (δ ¹³C_col, δ ¹⁵N_col) and human structural carbonate (δ ¹³C_sc) using skeletal material recovered from the Dalheim cemetery. Traditional interpretation of the isotopic data indicates that Dalheim residents likely relied on a C₃ plant-based diet and consumed some terrestrial animal products without evidence of marine resource input in the diet. Bivariate and multivariate models used as an additional means to assess diet indicate minor consumption of C₄ plant foods in this community. The multivariate-isotope model identified regional similarities and differences in C₄ plant/marine food consumption and in dietary protein sources by comparing data from Dalheim with those of other medieval sites from the published literature. We did not observe sex differences in this population but differences in δ ¹⁵N_col suggest that juveniles consumed the lowest trophic level protein.     

Diet and death in times of war: isotopic and osteological analysis of mummified human remains from southern Mongolia

This study presents the results of an isotopic analysis of nine naturally mummified individuals—three adults, two adolescents, one juvenile, and three infants—recovered from the Hets Mountain Cave site in southern Mongolia, where they had been secondarily deposited. All of the individuals show evidence of violent perimortem trauma, but no skeletal indicators of nutritional or disease-related stress. Multi-isotopic data (δ¹³C, δ¹⁵N, δ¹⁸O, ⁸⁷Sr/⁸⁶Sr, and ²⁰ⁿPb/²⁰⁴Pb) were characterized in multiple tissues from each individual when possible, in order to reconstruct diet composition and residential origin at different points in life. Specifically, δ¹³C and δ¹⁵N in bone carbonate and collagen (N = 8) and hair keratin (N = 4) were coupled with enamel carbonate δ¹⁸O and δ¹³C (N = 3) and enamel ⁸⁷Sr/⁸⁶Sr, and ²⁰ⁿPb/²⁰⁴Pb (N = 3) to assess diet and residential mobility in relation to skeletal indicators of health and trauma. Results are consistent with a persistence of mixed C₃/C₄ pastoral subsistence and general stability of diet composition over the life course, in contrast to contemporary accounts of widespread famine and a dependence on grains imported from China throughout the region. However, results also suggest that at least some individuals may have migrated to this region of southern Mongolia from elsewhere during life, meaning that their dietary isotopic profiles may not represent local subsistence patterns near the Hets Mountain Cave site. Overall, these results speak to the utility of life course oriented multi-isotopic analysis in complementing more top-down historical analyses in understanding variation in subsistence, nutrition, and migration in regions undergoing significant political and economic turmoil.     

The p‐Regions Problem. p‐区域问题

The p‐regions problem involves the aggregation or clustering of n small areas into p spatially contiguous regions while optimizing some criteria. The main objective of this article is to explore possible avenues for formulating this problem as a mixed integer‐programming (MIP) problem. The critical issue in formulating this problem is to ensure that each region is a spatially contiguous cluster of small areas. We introduce three MIP models for solving the p regions problem. Each model minimizes the sum of dissimilarities between all pairs of areas within each region while guaranteeing contiguity. Three strategies designed to ensure contiguity are presented: (1) an adaptation of the Miller, Tucker, and Zemlin tour‐breaking constraints developed for the traveling salesman problem; (2) the use of ordered‐area assignment variables based upon an extension of an approach by Cova and Church for the geographical site design problem; and (3) the use of flow constraints based upon an extension of work by Shirabe. We test the efficacy of each formulation as well as specify a strategy to reduce overall problem size.