A Route Map for Successful Applications of Geographically Weighted Regression

Geographically Weighted Regression (GWR) is increasingly used in spatial analyses of social and environmental data. It allows spatial heterogeneities in processes and relationships to be investigated through a series of local regression models rather than a single global one. Standard GWR assumes that relationships between the response and predictor variables operate at the same spatial scale, which is frequently not the case. To address this, several GWR variants have been proposed. This paper describes a route map to decide whether to use a GWR model or not, and if so which of three core variants to apply: a standard GWR, a mixed GWR or a multiscale GWR (MS-GWR). The route map comprises 3 primary steps that should always be undertaken: (1) a basic linear regression, (2) a MS-GWR, and (3) investigations of the results of these in order to decide whether to use a GWR approach, and if so for determining the appropriate GWR variant. The paper also highlights the importance of investigating a number of secondary issues at global and local scales including collinearity, the influence of outliers, and dependent error terms. Code and data for the case study used to illustrate the route map are provided.     

Exploring the Relations Between Riverbank Erosion and Geomorphological Controls Using Geographically Weighted Logistic Regression

The relations between riverbank erosion and geomorphological variables that are thought to control or influence erosion are commonly modelled using regression. For a given river, a single regression model might befitted to data on erosion and its geomorphological controls obtained along the river's length. However, it is likely that the influence of some variables may vary with geographical location (i.e., distance upstream). For this reason, the spatially stationary regression model should be replaced with a non‐stationary equivalent. Geographically weighted regression (GWR) is a suitable choice. In this paper, GWR is extended to predict the binary presence or absence of erosion via the logistic model. This extended model was applied to data obtained from historical archives and a spatially intensive field survey of a length of 42 km of the Afon Dyfi in West Wales. The model parameters and the residual deviance of the model varied greatly with distance upstream. The practical implication of the result is that different management practices should be implemented at different locations along the river. Thus, the approach presented allowed inference of spatially varying management practice as a consequence of spatially varying geomorphological process.     

Dynamics of Land Surface Temperature in Response to Land‐Use/Cover Change

In this study, we employed Geographical Information Systems and remote sensing techniques to investigate the impact of land‐use/cover change on land surface temperature (LST) in a rapidly urbanisation city, Kunming in south‐west China. Spatial patterns of LST and land use for 1992 and 2006 were derived from Landsat images to examine how LST responded to urban growth. Remote sensing indices were used to quantify land‐use types and employed as explanatory variables in LST modelling. The geographically weighted regression (GWR), a location dependent model, was performed to explore the influences of the spatially varied land‐use conditions on the LST patterns. Results revealed that rapid urbanisation in Kunming altered the local thermal environment, particularly in increasing the LST in the zone surrounding the urban core. Remote sensing indices demonstrated that water and vegetation played an important role in mitigating the urban heat island effect, while built‐up and barren land accounted for the increase in LST. The GWR improved the goodness‐of‐fit for LST modelling and provided insights into the spatially varied relationship between LST and land‐use conditions.     

The Determinants of Regional Freight Transport: A Spatial,Semiparametric Approach

In the context of modeling regional freight the four‐stage model is a popular choice. The first stage of the model, freight generation and attraction, however, suffers from three shortcomings: first of all, it does not take spatial dependencies among regions into account, thus potentially yielding biased estimates. Second, there is no clear consensus in the literature as to the choice of explanatory variables. Second, sectoral employment and gross value added are used to explain freight generation, whereas some recent publications emphasize the importance of variables which measure the amount of logistical activity in a region. Third, there is a lack of consensus regarding the functional form of the explanatory variables. Multiple recent studies emphasize nonlinear influences of selected variables. This article addresses these shortcomings by using a spatial variant of the classic freight generation and attraction models combined with a penalized spline framework to model the explanatory variables in a semiparametric fashion. Moreover, a Bayesian estimation approach is used, coupled with a penalized Normal inverse‐Gamma prior structure, to introduce uncertainty regarding the choice and functional form of explanatory variables. The performance of the model is assessed on a real‐world example of freight generation and attraction of 258 European NUTS‐2 level regions, covering 25 European countries.     

Some Notes on Parametric Significance Tests for Geographically Weighted Regression

The technique of geographically weighted regression (GWR) is used to model spatial 'drift' in linear model coefficients. In this paper we extend the ideas of GWR in a number of ways. First, we introduce a set of analytically derived significance tests allowing a null hypothesis of no spatial parameter drift to be investigated. Second, we discuss 'mixed' GWR models where some parameters are fixed globally but others vary geographically. Again, models of this type may be assessed using significance tests. Finally, we consider a means of deciding the degree of parameter smoothing used in GWR based on the Mallows C_p statistic. To complete the paper, we analyze an example data set based on house prices in Kent in the U.K. using the techniques introduced.     

基于GWR模型的合肥居住地价影响因素研究

以合肥市主城区为例,基于2010-2014年居住用地的出让数据,运用地统计法、GWR模型等方法,对合肥市居住地价的空间异质性及其影响因素进行研究。研究表明：①合肥市居住地价的空间分布呈现出显著的多中心的空间结构,地价的峰值区分别以老城区、政务区天鹅湖及滨湖新区塘西河公园为中心呈现圈层式分布;②不同的地价影响因素表现出不同的空间分布特征,其中容积率对居住地价的贡献度空间差异最大,其次是宗地面积,主干路次之,交通站点对居住地价的贡献度最小;③厘清各影响因素对地价的作用机制,建立动态的数字地价模型,不仅能促进土地资源的集约利用,重塑城市的空间结构,而且能为城市整体价值的发挥提供重要的理论支撑。     

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.     

BAYESIAN MODEL AVERAGING IN THE CONTEXT OF SPATIAL HEDONIC PRICING: AN APPLICATION TO FARMLAND VALUES

ABSTRACT Specification uncertainty arises in spatial hedonic pricing models because economic theory provides no guide in choosing the spatial weighting matrix and explanatory variables. Our objective in this paper is to investigate whether we can resolve uncertainty in the application of a spatial hedonic pricing model. We employ Bayesian Model Averaging in combination with Markov Chain, Monte Carlo Model Composition. The proposed methodology provides inclusion probabilities for explanatory variables and weighting matrices. These probabilities provide a clear indication of which explanatory variables and weighting matrices are most relevant, but they are case specific.     

The Spatial Association of Demographic and Population Health Characteristics with COVID-19 Prevalence Across Districts in India

In less-developed countries, the lack of granular data limits the researcher's ability to study the spatial interaction of different factors on the COVID-19 pandemic. This study designs a novel database to examine the spatial effects of demographic and population health factors on COVID-19 prevalence across 640 districts in India. The goal is to provide a robust understanding of how spatial associations and the interconnections between places influence disease spread. In addition to the linear Ordinary Least Square regression model, three spatial regression models—Spatial Lag Model, Spatial Error Model, and Geographically Weighted Regression are employed to study and compare the variables explanatory power in shaping geographic variations in the COVID-19 prevalence. We found that the local GWR model is more robust and effective at predicting spatial relationships. The findings indicate that among the demographic factors, a high share of the population living in slums is positively associated with a higher incidence of COVID-19 across districts. The spatial variations in COVID-19 deaths were explained by obesity and high blood sugar, indicating a strong association between pre-existing health conditions and COVID-19 fatalities. The study brings forth the critical factors that expose the poor and vulnerable populations to severe public health risks and highlight the application of geographical analysis vis-a-vis spatial regression models to help explain those associations.     

Inference in Multiscale Geographically Weighted Regression

A recent paper expands the well-known geographically weighted regression (GWR) framework significantly by allowing the bandwidth or smoothing factor in GWR to be derived separately for each covariate in the model—a framework referred to as multiscale GWR (MGWR). However, one limitation of the MGWR framework is that, until now, no inference about the local parameter estimates was possible. Formally, the so-called “hat matrix,” which projects the observed response vector into the predicted response vector, was available in GWR but not in MGWR. This paper addresses this limitation by reframing GWR as a Generalized Additive Model, extending this framework to MGWR and then deriving standard errors for the local parameters in MGWR. In addition, we also demonstrate how the effective number of parameters can be obtained for the overall fit of an MGWR model and for each of the covariates within the model. This statistic is essential for comparing model fit between MGWR, GWR, and traditional global models, as well as for adjusting multiple hypothesis tests. We demonstrate these advances to the MGWR framework with both a simulated data set and a real-world data set and provide a link to new software for MGWR (MGWR1.0) which includes the novel inferential framework for MGWR described here.     

Modélisation spatiale de la pauvretéà Montréal: apport méthodologique de la régression géographiquement pondérée

Spatial Modeling of Poverty in Montréal: Methodological Contribution of the Geographically Weighted Regression
The Island of Montréal is particularly concerned with the issue of poverty. In 2000, 29 percent of its inhabitants lived under the low income cut-offs as defined by Statistics Canada. However, poverty is not a homogeneous phenomenon at the intra-urban scale, and identifying and categorizing spaces of poverty has become a main concern for ongoing researches. According to this way of thinking, this paper proposes an analysis of the factors influencing the geographical distribution of poverty on the Island of Montréal. To be able to identify properly the various profiles of poverty, this analysis uses a specific methodology, the geographically weighted regression (GWR), and compares its results with the ones of a classical regression model. At the global level, the most important factors to explain poverty are in order: unemployment, lone-parent families, one person households, recent immigrants, part time or part year workers, school dropouts. At the local level,     

Gaussian Process Regression and Bayesian Model Averaging: An Alternative Approach to Modeling Spatial Phenomena

Gaussian Process Regression (GPR) is a nonparametric technique that is capable of yielding reliable out‐of‐sample predictions in the presence of highly nonlinear unknown relationships between dependent and explanatory variables. But in terms of identifying relevant explanatory variables, this method is far less explicit about questions of statistical significance. In contrast, more traditional spatial econometric models, such as spatial autoregressive models or spatial error models, place rather strong prior restrictions on the functional form of relationships, but allow direct inference with respect to explanatory variables. In this article, we attempt to combine the best of both techniques by augmenting GPR with a Bayesian Model Averaging (BMA) component that allows for the identification of statistically relevant explanatory variables while retaining the predictive performance of GPR. In particular, GPR‐BMA yields a posterior probability interpretation of model‐inclusion frequencies that provides a natural measure of the statistical relevance of each variable. Moreover, while such frequencies offer no direct information about the signs of local marginal effects, it is shown that partial derivatives based on the mean GPR predictions do provide such information. We illustrate the additional insights made possible by this approach by applying GPR‐BMA to a benchmark BMA data set involving potential determinants of cross‐country economic growth. It is shown that localized marginal effects based on partial derivatives of mean GPR predictions yield additional insights into comparative growth effects across countries.     

Spatial and Scale‐Dependent Controls on North American Pan‐Arctic Minimum River Discharge

Spatial patterns of minimum monthly river discharge in the North American Pan‐Arctic and its potential controls are explored with geographically weighted regression (GWR). Minimum discharge is indicative of soil water conditions; therefore, understanding spatial variability of its controls may provide insights into patterns of hydrologic change. Here, GWR models are applied to determine a suitable combination of independent variables selected from a set of eight variables. A model specification with annual mean river discharge, temperature at time of minimum discharge, and biome describes well the spatial patterns in minimum discharge. However, minimum discharge in larger watersheds is influenced more by temperature and biome distributions than it is in small basins, suggesting that scale is critical for understanding minimum river discharge. This study is the first to apply GWR to explore spatial variation in Pan‐Arctic hydrology. Factores de control espaciales y dependientes de escala en las descargas fluviales mínimas de ríos Pan‐Articos en Norteamérica. El artículo explora los patrones espaciales de caudales fluviales mínimos mensuales la región pan‐ártica de Norteamérica y sus posibles factores de control haciendo uso de una regresión ponderada geográficamente (geographically weigted regression‐GWR). Los caudales mínimos son indicadores de las condiciones del agua en el suelo, y por lo tanto el entendimiento de la variabilidad espacial de los factores que los controlan puede ayudar a comprender los patrones de cambio hidrológico. En el presente estudio, varios modelos de tipo GWR son aplicados para determinar una combinación adecuada de variables independientes seleccionadas a partir de un conjunto de ocho variables. El modelo que utiliza la media anual media de descarga fluvial, la temperatura en el momento de caudal mínimo, y el bioma, proporciona una buena descripción de los patrones espaciales en la descarga mínima. Sin embargo, en las cuencas hidrográficas grandes, la descarga mínima está más influenciada por la temperatura y la distribución de los biomas que en el caso de cuencas más pequeñas, lo que sugiere que la escala es fundamental para entender la descarga mínima fluvial. Este estudio es el primero en aplicar GWR para comprender la variación espacial en la hidrología de la región pan‐ártica. 基于GWR（地理加权回归模型）对北美泛北极地区月份最小河流流量的空间模式和潜在控制进行研究。最小流量暗示水土条件;因此,理解空间分异及控制可深刻理解水文变化的模式。GWR可从8个变量中提取一组独立变量的适当组合。通过年均河流流量、最小流量时的温度和生物群落,来描述最小下泄流量的空间格局。在大范围流域中,最小流量受到温度和生物群落分布的影响大于在小规模的流域,揭示出在河流最小流量分析中尺度是非常重要的。本文首次将GWR应用于泛北极水文空间异质性分析。     

Bayesian Model Averaging for Spatial Econometric Models

We extend the literature on Bayesian model comparison for ordinary least-squares regression models to include spatial autoregressive and spatial error models. Our focus is on comparing models that consist of different matrices of explanatory variables. A Markov Chain Monte Carlo model composition methodology labeled MC ³ by Madigan and York is developed for two types of spatial econometric models that are frequently used in the literature. The methodology deals with cases where the number of possible models based on different combinations of candidate explanatory variables is large enough such that calculation of posterior probabilities for all models is difficult or infeasible. Estimates and inferences are produced by averaging over models using the posterior model probabilities as weights, a procedure known as Bayesian model averaging. We illustrate the methods using a spatial econometric model of origin–destination population migration flows between the 48 U.S. states and the District of Columbia during the 1990–2000 period.     

通勤时间的幸福绩效——基于中国家庭追踪调查的实证研究

幸福不仅是个人的心愿,也是城市管理者的执政目标之一,因此,对于城市中普遍存在的通勤时间过长所带来的心理影响研究十分必要。本文采用中国家庭追踪调查(CFPS)数据,考察了通勤时间对于个人主观幸福感的影响。实证结果显示,通勤时间对于个人幸福感存在显著的负向影响,随着个人通勤时间的增加,个人幸福感也随之降低。通勤时间与生活满意度也同样呈现显著的负相关,这也证明了结论的稳健性。通过进一步考察通勤时间负面影响的异质性发现,通勤时间对幸福感的影响在不同社会群体间存在差异,对于个人收入高、教育程度高、家庭收入高的居民而言,通勤时间所造成的负面心理影响更大。因此,政府应重视通勤对居民幸福感的影响,并致力于提高交通效率。     

A battle in the Bush: Some lessons from liberal‐national rivalry in Warrnambool

An intriguing aspect of rural Australian politics has been the occasional capacity of one of the conservative parties to make sudden, substantial electoral gains at the other's expense. C.A. Hughes (1985:53) has suggested that, in order to understand Liberal‐National rivalry, we ought not dwell upon demographic variables but need undertake detailed electoral studies and draw out the importance of ‘the personalities and local popularity of candidates’. Such a micro‐level of political examination, he laments, is rarely attempted in Australia. Ours is a micro‐level study of the one‐time safe Liberal Victorian state seat of Warrnambool in which, in recent elections (1985 and 1988), the National Party has decisively wrested control. Certainly the local popularity of the National Party candidates contributed in no small way to the switch in conservative allegiance which has occurred in Warrnambool. However, contra Hughes, we also identify an important demographic explanatory variable in Catholicism.     

Calibration and Test of a Discrete Choice Model with Endogenous Choice Sets

Conventional discrete choice models assume implicitly that the choice set is independent of the decisionmaker's preferences conditional on the explanatory variables of the models. This assumption is implausible in many choice situations where the decisionmaker selects his or her choice set. This paper estimates and tests a discrete choice model with endogenous choice sets based on Horowitz' theoretical work. To calibrate the model, a new probability simulator is introduced and a sequential estimation procedure is developed. The model and calibration methods are tested in an empirical application as well as Monte Carlo simulations. The empirical results are used to test the theory of endogenous choice sets and to examine the differences between the new model and a conventional choice model in parameter estimates and predicted choice probabilities. The empirical results strongly suggest that ignoring the endogeneity of choice sets in choice modeling can have serious consequences in applications.     

The Multiple Testing Issue in Geographically Weighted Regression

This article describes the problem of multiple testing within a Geographically Weighted Regression framework and presents a possible solution to the problem which is based on a family‐wise error rate for dependent processes. We compare the solution presented here to other solutions such as the Bonferroni correction and the Byrne, Charlton, and Fotheringham proposal which is based on the Benjamini and Hochberg False Discovery Rate. We conclude that our proposed correction is superior to others and that generally some correction in the conventional t‐test is necessary to avoid false positives in GWR.     

Single and Multiscale Models of Process Spatial Heterogeneity

Recent work in local spatial modeling has affirmed and broadened interest in multivariate local spatial analysis. Two broad approaches have emerged: Geographically Weighted Regression (GWR) which follows a frequentist perspective and Bayesian Spatially Varying Coefficients models. Although several comparisons between the two approaches exist, recent developments, particularly in GWR, mean that these are incomplete and missing some important axes of comparison. Consequently, there is a need for a more thorough comparison of the two families of local estimators, including recent developments in multiscale variants and their relative performance under controlled conditions. We find that while both types of local models generally perform similarly on a series of criteria, some interesting and important differences exist.     

THE ECONOMICS OF AIR TRAVEL GRAVITY MODELS*

Starting with the aggregate demand model of economics, a model of demand for intercity air travel is developed which contains the gravity model as a less general submodel. The more general model is referred to as the alternative opportunities model since it takes account of alternative destinations open to travelers, not just origin and destination as does the gravity model. The demand model approach has the virtue of providing a theoretical basis for understanding and analyzing the gravity model. The gains from treating alternative locations and demand motivation variables are a substantial increase in explanatory power over that yielded by the gravity model, the identification of statistically significant determinants of air travel, and better measurement of the coefficients of population and distance by taking account of these other variables and somewhat better forecasts. A shortcoming of procedures used here is aggregation of air trips with different purposes and thus lack of clear specification of the size of effects of different variables on different types of travel. Overcoming this difficulty must await origin-destination data listed by trip purpose.