Measuring Impacts of Condition Variables in Rule‐Based Models of Space‐Time Choice Behavior: Method and Empirical Illustration

The use of rule‐based systems for modeling space‐time choice has gained increasing research interests over the last years. The potential advantage of the rule‐based approach is that it can handle interactions between a large set of predictors. Decision tree induction methods are available and have been explored for deriving rules from data. However, the complexity of the structures that are generated by such knowledge discovery methods hampers an interpretation of the rule‐set in behavioral terms with as a consequence that the models typically remain a black box. To solve this problem, this paper develops a method for measuring the size and direction of the impact of condition variables on the choice variable as predicted by the model. The paper illustrates the method based on location and transport‐mode choice models that are part of Albatross model—an activity‐based model of space‐time choice.     

Investigating the Influence of Spatial and Temporal Granularities on Agent‐Based Modeling

Epidemic agent‐based models (ABMs) simulate individuals in artificial societies that are capable of movement, interaction, and transmitting disease among themselves. ABMs have been used to study the spread of disease at various spatial and temporal scales ranging from small communities to the world, over days, months, and years. The representations of space and time often vary between different epidemic ABMs and can be influenced by factors such as the size of a modeled population, computational requirements, population environments, and disease‐related data. The influence that the representations of space and time have on epidemic ABMs is difficult to assess. Here we show that the finest representations of space and time—termed spatial and temporal granularities (STGs)—in a parsimonious ABM affect speed, intensity, and spatial spread of a synthetic disease. Specifically, we found disease spread faster and more intensely as spatial granularity is coarsened, whereas disease spread slower and less intensely as temporal granularity is coarsened in a parsimonious ABM. Our study is the first to use the same epidemic ABM to examine the influence of STGs. Our results demonstrate that STGs influence ABM dynamics including early disease burnout and that an interrelationship exists between the coarsening of STGs and the speed and intensity at which disease spreads. Our parsimonious ABM is extended based on a structured community model and we found STGs also influence ABM dynamics in a more realistic context that includes hierarchical movement. Broadly, our study serves as a basis for further inquiry toward the influence of space–time representations on more realistic models that include multiscale mobility, routine movements (e.g., commuting), and heterogeneous population distributions.     

Latent trajectory models for space‐time analysis: An application in deciphering spatial panel data

This article introduces latent trajectory models (LTMs), an approach often employed in social sciences to handle longitudinal data, to the arena of GIScience, particularly space‐time analysis. Using the space‐time data collected at county level for the whole United States through webpage search on the keyword “climate change,” we show that LTMs, when combined with eigenvector filtering of spatial dependence in data, are very useful in unveiling temporal trends hidden in such data: the webpage‐data derived popularity measure for climate change has been increasing from December 2011 to March 2013, but the increase rate has been slowing down. In addition, LTMs help reveal potential mechanisms behind observed space‐time trajectories through linking the webpage‐data derived popularity measure about climate change to a set of socio‐demographic covariates. Our analysis shows that controlling for population density, greater drought exposure, higher percent of people who are 16 years old or above, and higher household income are positively predictive of the trajectory slopes. Higher percentages of Republicans and number of hot days in summer are negatively related to the trajectory slopes. Implications of these results are examined, concluding with consideration of the potential utility of LTMs in space‐time analysis and more generally in GIScience.     

Spatio‐Temporal Modelling As A Way to Reconstruct Patterns of Past Human Activities

This paper examines the possibilities of creating quantified models of past human activities in both time and space. The study area lies in the south‐eastern Czech Republic and western Slovakia. The spatio‐temporal model of behavioural categories was calculated with the help of Monte Carlo simulations and statistical testing. One of the main advantages of our approach is that it admits the probabilistic nature of input data, quantifies them and provides probabilistic results comparable with other proxies. It also presents a less biased way of how archaeological data from regions and periods with low numbers of ¹⁴C datings can be incorporated into models of past population dynamics.     

Quantitative basin modeling: present state and future developments towards predictability

A critique review of the state of quantitative basin modeling is presented. Over the last 15 years, a number of models are proposed to advance our understanding of basin evolution. However, as of present, most basin models are two dimensional (2‐D) and subject to significant simplifications such as depth‐ or effective stress‐dependent porosity, no stress calculations, isotropic fracture permeability, etc. In this paper, promising areas for future development are identified. The use of extensive data sets to calibrate basin models requires a comprehensive reaction, transport, mechanical (RTM) model in order to generate the synthetic response. An automated approach to integrate comprehensive basin modeling and seismic, well‐log and other type of data is suggested. The approach takes advantage of comprehensive RTM basin modeling to complete an algorithm based on information theory that places basin modeling on a rigorous foundation. Incompleteness in a model can self‐consistently be compensated for by an increase in the amount of observed data used. The method can be used to calibrate the transport, mechanical, or other laws underlying the model. As the procedure is fully automated, the predictions can be continuously updated as new observed data become available. Finally, the procedure makes it possible to augment the model itself as new processes are added in a way that is dictated by the available data. In summary, the automated data/model integration places basin simulation in a novel context of informatics that allows for data to be used to minimize and assess risk in the prediction of reservoir location and characteristics.     

A Hybrid Framework for Space–Time Modeling of Environmental Data. 环境数据时空建模的混合框架

The space–time autoregressive integrated moving average (STARIMA) model family provides useful tools for modeling space–time processes that exhibit stationarity (or near stationarity) in space and time. However, a more general method for routine use and efficient computation is needed to model the nonlinearities and nonstationarities of environmental space–time series. This article presents a hybrid framework combining machine learning and statistical methods to address this issue. It uses an artificial neural network (ANN) to extract global deterministic (nonlinear) space–time trends and a STARIMA model to extract local stochastic space–time variations in data. A four‐stage procedure is proposed for analyzing and modeling space–time series. The proposed framework and procedures are applied to forecast annual average temperature at 137 national meteorological stations in China. The results demonstrate that the hybrid framework achieves better forecasting accuracy than the STARIMA model alone. This finding suggests that the combination of machine learning and statistical methods provides a very powerful tool for analyzing and modeling space–time series of environmental data that have strong spatial nonlinear and nonstationary components.     

Microeconomic Formulation and Estimation of a Residential Location Choice Model: Implications for the Value of Time

Abstract We formulate a microeconomic model of residential location choice behavior as an aggregate of the individual behaviors of household members, subject to individual time constraints and a common income budget. A simplified version of the model is estimated from stated preference rank‐order data, yielding a function that may be interpretated as a conditional indirect utility function. We consider Box‐Tukey transformations, segmentation by income class, and a consistent treatment of data at different rank depths using the simultaneous mixed‐estimation method. Measures of the household's willingness‐to‐pay (through rents) for reducing travel times to work and study in the short run, are interpreted as subjective values of time and compared with such values derived from mode choice models. Our results are plausible, and consistent with recent findings showing that the short‐run benefits of transport projects derived by transport models are larger than benefits measured at the land use system.     

Time‐Dependent Functions for Avoidance Behaviors Made in Response to the Circulation of HIV and AIDS

Interventions aimed at preventing HIV transmission include avoidance behaviors like condom use and reduced partner acquisition. In turn., engagement in such activities might also entail changed patterns of travel to evade contact with infected individuals. One method of estimating the effects of these actions on the observed distribution of HIV/AIDS involves the specification of space‐time models that imitate the epidemic process. This paper presents an application of this procedure where prevention is construed as a continuous population response to the evolving distribution of HIV and AIDS. This task entails the construction of models with time‐dependent parameters adapted to predicted prevalence or incidence measures to represent the effects of specific avoidance behaviors. In this respect, a multiregion model is described that serves as a baseline for analyzing the impact of preventative actions on the HIV/AIDS epidemic in Western Europe. A series of adaptation functions are derived within this system for imitating both changed rates of partner acquisition and altered travel behaviors. The results elicit modifications to the behavior of the baseline epidemic that are generated by each of these functions. Then, the conditions supporting space‐time variations in rates of survival between core countries (relatively low) and those in the periphery (relatively high) are investigated. The discussion considers the implications of these results for health policies that promote avoidance behaviors.     

Dealing with Timing and Synchronization in Opportunities for Joint Activity Participation. 公共活动参与机会中实时性与同步性处理

The ability of people to access opportunities offered by the built environment is circumscribed by various sets of space–time constraints, including the requirements to meet other persons at particular times and places to undertake activities together. While models of space–time accessibility recognize that joint activities may constrain the performance of activities in space and time, their specifications do not explicitly acknowledge the opportunities that individuals of a group have for joint activity participation. Therefore, this article focuses on joint activity participation and argues that collective activity decisions are the outcome of a complex process involving various aspects of timing, synchronization, and social hierarchy. The utility‐theoretic model proposed here quantifies the extent to which opportunities can be jointly accessed by a particular group of people within a specific time period. Central to the approach are three key variables: the attractiveness of an opportunity, the time available for activity participation, and the travel time to an activity location. Because of the multiperson character of joint activities, the determination of these variables is subject to individual preferences, privileges, and power differentials within a group. Specific attention is given to how time‐of‐day and synchronization effects influence the opportunities accessible to a group of individuals. The impact of these factors on joint accessibility is illustrated by a real‐world example of an everyday rendezvous scenario. The outcomes of a simulation exercise suggest that time‐of‐day and synchronization effects significantly affect the benefits that can be gained from opportunities for joint activities.     

Analyzing Space–Time Crime Incidents Using Eigenvector Spatial Filtering: An Application to Vehicle Burglary

Poisson models generally are utilized in analyzing spatial patterns of crime count data. When spatial autocorrelation is present, these models are extended to account for it. Among various methods, eigenvector spatial filtering (ESF) furnishes an efficient means of analysis. However, because space–time crime data have temporal components as well as spatial components, Poisson models need to be further adjusted to reflect the two types of components simultaneously. This article discusses how the ESF method can be utilized to model space–time crime data, extending the generalized linear mixed model specification for it. This approach is illustrated with an application to space–time vehicle burglary incidents in the city of Plano, Texas, during 2004–2009. Los modelos de Poisson generalmente se utilizan en el análisis de los patrones espaciales de los datos de recuento de crimen. Cuando hay autocorrelación espacial, estos modelos son modificados para dar cuenta de ello. Entre los diversos métodos existentes, el método Eigenvector (autovector, vector propio) de filtrado espacial (Eigenvector Spatial Filtering‐ESF) proporciona un medio eficaz para dicho análisis. Sin embargo, dado que los datos de criminalidad espacio‐temporales tienen tanto componentes temporales como espaciales, los modelos tipo Poisson requieren de un ajuste adicional para reflejar ambos tipos de componentes de manera simultánea. El artículo presente expone cómo el método ESF puede ser utilizado para modelar datos espacio‐temporales sobre delitos mediante la modificación del modelo mixto lineal generalizado (Generalized Linear Mixed Model‐GLMM). El procedimiento propuesto se ilustra con el caso de incidentes espacio‐temporales de robos de vehículos en la ciudad de Plano, Texas, durante 2004–2009. 泊松模型一般用于犯罪计数数据的空间模式分析中,当空间自相关关系呈现时,这类模型可扩展以解释潜在的分布特征。在各种模型中,特征向量空间滤波（ESF）提供了一种有效的分析方法。然而,由于时空犯罪数据包含时间和空间组分,因此泊松模型需要进一步调整以同时反映这两种不同类型的数据。本文讨论了如何利用特征向量空间滤波(ESF)模型对时空犯罪数据进行建模,并采用扩展广义线性混合模型(GLMM)进行规范。最后,以德克萨斯州普莱诺市2004‐2009年的车辆盗窃案数据进行了实证验证。     

Geographical and Temporal Weighted Regression (GTWR)

Both space and time are fundamental in human activities as well as in various physical processes. Spatiotemporal analysis and modeling has long been a major concern of geographical information science (GIScience), environmental science, hydrology, epidemiology, and other research areas. Although the importance of incorporating the temporal dimension into spatial analysis and modeling has been well recognized, challenges still exist given the complexity of spatiotemporal models. Of particular interest in this article is the spatiotemporal modeling of local nonstationary processes. Specifically, an extension of geographically weighted regression (GWR), geographical and temporal weighted regression (GTWR), is developed in order to account for local effects in both space and time. An efficient model calibration approach is proposed for this statistical technique. Using a 19‐year set of house price data in London from 1980 to 1998, empirical results from the application of GTWR to hedonic house price modeling demonstrate the effectiveness of the proposed method and its superiority to the traditional GWR approach, highlighting the importance of temporally explicit spatial modeling.     

A Data Science Framework for Movement

Movement is the driving force behind the form and function of many ecological and human systems. Identification and analysis of movement patterns that may relate to the behavior of individuals and their interactions is a fundamental first step in understanding these systems. With advances in IoT and the ubiquity of smart connected sensors to collect movement and contextual data, we now have access to a wealth of geo‐enriched high‐resolution tracking data. These data promise new forms of knowledge and insight into movement of humans, animals, and goods, and hence can increase our understanding of complex spatiotemporal processes such as disease outbreak, urban mobility, migration, and human‐species interaction. To take advantage of the evolution in our data, we need a revolution in how we visualize, model, and analyze movement as a multidimensional process that involves space, time, and context. This paper introduces a data science paradigm with the aim of advancing research on movement.     

Forecasting in a Small and Unstable Regional Economy Using Regime Shifting Models: The Case of Extremadura

We consider forecasting in a small and unstable regional economy subject to structural breaks. In this context, we work with two types of regime‐shifting databased models using cointegration theory. The objective of the present work is to analyze the out‐of‐sample forecasting performance of the two approaches used to construct a short‐term regional econometric model: stochastic and deterministic time varying parameters models. The forecasting experiments will be illustrated by specifying, and estimating an econometric model for Extremadura, a small and unstable region in southwestern Spain.     

A coarse Bayesian approach to evaluate luminescence ages

This paper develops a simplified Bayesian approach to evaluate a luminescence age. We limit our purpose to the cause-effect relationship between the age and the accumulated dose. The accumulated dose is given as a function of the age and several others parameters: internal radionuclides contents, gamma dose rate, cosmic dose rate, alpha efficiency, wetness, conversion factors, wetness coefficients, fading rate and storage time. The age is the quantity we are looking for. Bayes’ theorem expresses the changes on the probability distribution of age due to the luminescence study. The information before study (prior) comprises what is previously known about the age and the archaeological model (cultural period, stratigraphic relations, type, etc.) as well as the parameters of the physical model. The accumulated dose consists in the data describing the measurement. The various stages of Bayesian approach were implemented using the software WinBugs. Simulated data sets were used in various models. We present various small models representing typical examples encountered in luminescence dating.     

Spatial Dimensions of the Easterlin Hypothesis: Fertility Variations in Italy

The paper re–evaluates the Easterlin hypothesis in a multiregional context by conceptually and methodologically accounting for two processes of spatial interdependence in an open subnational demo–economic system: diffusion of fertility norms and values across space, and movements between labor markets. The empirical analysis estimates pooled cross–sectional, time–series models using data for 18 Italian regions from 1952 to 1995. The results suggest that accounting for spatial interdependencies is necessary to avoid model misspecifications. Moreover, the models lead to space–time landscapes of fertility elasticities that suggest, for the majority of space–time units, an inverse Easterlin effect for the diffusion component but support of the Easterlin hypothesis due to labor movements across space.     

Is “Threat” in the Eye of the Researcher? Theory and Measurement in the Study of State‐Level Immigration Policymaking

This study initiates a methodological critique of the state‐level immigration policy literature through the lens of the racial threat and group power perspectives. First, I highlight the conceptual problems related to the application of such theories to legislature‐level data analysis. Next, I demonstrate the methodological and analytical problems that raise concerns about ad hoc theorizing in this field. Using counts of hostile and welcoming immigration legislation (2005–2011), I demonstrate that outgroup size measures correlate positively with both dependent variables while measures of population growth rate yield null results unless used on their own. These results suggest that the use of legislature‐level models with demographic indicators does not allow us to gain a clear understanding of whether and how population dynamics influence immigration policymaking. Based on these findings, I recommend that when using demographic indicators as key explanatory variables, researchers provide evidence of result consistency across multiple model specifications and also test the models with both hostile and inclusive policy variables. Such protocols would help avoid ad hoc theorizing.     

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.     

GIS Methods in Time-Geographic Research: Geocomputation and Geovisualization of Human Activity Patterns

Over the past 40 years or so, human activities and movements in space‐time have attracted considerable research interest in geography. One of the earliest analytical perspectives for the analysis of human activity patterns and movements in space‐time is time geography. Despite the usefulness of time geography in many areas of geographical research, there are very few studies that actually implemented its constructs as analytical methods up to the mid‐1990s. With increasing availability of geo‐referenced individual‐level data and improvement in the geo‐computational capabilities of Geographical Information Systems (GIS), it is now more feasible than ever before to operationalize and implement time‐geographic constructs. This paper discusses recent applications of GIS‐based geo‐computation and three‐dimensional (3‐D) geo‐visualization methods in time‐geographic research. The usefulness of these methods is illustrated through examples drawn from the author's recent studies. The paper attempts to show that GIS provides an effective environment for implementing time‐geographic constructs and for the future development of operational methods in time‐geographic research.     

Aggregation of Regional Economic Time Series with Different Spatial Correlation Structures. 具有不同空间相关结构的区域经济时间序列集成

In this article, we compare the relative efficiency of different forecasting methods of space‐time series when variables are spatially and temporally correlated. We consider two cases: (1) univariate forecasting (i.e., a space‐time series aggregated into a single time series) and (2) the more general instance of multivariate forecasting (i.e., a space‐time series aggregated into a coarser spatial partition). We extend the results in the literature by including the consideration of larger datasets and the treatment of edge effects and of negative spatial correlation. We first introduce a statistical framework based on the space‐time autoregressive class of random field models, which constitutes the basis of our simulation study, and we present the various alternative forecasting methods considered in the simulation. We then present the results of a Monte Carlo study related to univariate forecasting. In order to allow a comparison with the findings of Giacomini and Granger (2004), we consider the same forecasting strategies and the same combinations of the parameter values used there, but with a larger parametric set. Finally, we extend our analysis to the case of multivariate forecasting. The outcomes obtained provide operational suggestions about how to choose between alternative forecasting methods in empirical circumstances.     

MODELING SPATIAL AUTOCORRELATION IN SPATIAL INTERACTION DATA: AN APPLICATION TO PATENT CITATION DATA IN THE EUROPEAN UNION*

ABSTRACT Spatial interaction models of the gravity type are widely used to model origin–destination flows. They draw attention to three types of variables to explain variation in spatial interactions across geographic space: variables that characterize an origin region of a flow, variables that characterize a destination region of a flow, and finally variables that measure the separation between origin and destination regions. This paper outlines and compares two approaches, the spatial econometric and the eigenfunction‐based spatial filtering approach, to deal with the issue of spatial autocorrelation among flow residuals. An example using patent citation data that capture knowledge flows across 112 European regions serves to illustrate the application and the comparison of the two approaches.