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.     

Neural Network Modeling of Constrained Spatial Interaction Flows: Design, Estimation, and Performance Issues

In this paper a novel modular product unit neural network architecture is presented to model singly constrained spatial interaction flows. The efficacy of the model approach is demonstrated for the origin constrained case of spatial interaction using Austrian interregional telecommunication traffic data. The model requires a global search procedure for parameter estimation, such as the Alopex procedure. A benchmark comparison against the standard origin constrained gravity model and the two–stage neural network approach, suggested by Openshaw (1998), illustrates the superiority of the proposed model in terms of the generalization performance measured by ARV and SRMSE.     

Telephone Communication Patterns in Austria: A Comparison of the IPFP-based Graph-Theoretic and the Intramax Approaches

Two alternative methodological approaches (the IPFP-based and the intramax procedures) to the problem of pattern identification in spatial interaction data are compared and evaluated in this paper. After a general discussion of the major characteristics and shortcomings of these methodologies, the paper presents the findings of a case study relying on telecommunication data measured by the Austrian PTT in 1991, in terms of erlangs. The results clearly illustrate the superiority of the intramax approach in the context of medium-sized and relatively centralized flow systems.     

Altpersisch taumani “kräfte”

Ohne Zusammenfassung     

“… daß der Liebhaber etwas Erfreuliches und Nützliches zu leisten im Stande ist.” Goethe,Soemmerring und das Os intermaxillare beim Menschen

Goethe's theoretical comments on the acknowledgement of the natural sciences dilettante differ considerably from his own experiences in this role (Farbenlehre, Zwischenkieferknochen) of dilettante. Therefore, it seems necessary to raise general questions on the concept: dilettante of natural sciences during Goethe's time, furthermore, on the characterization and labeling of such a dilettante in an historical-scientific context. This is especially important since up to the present time this particular problem has hardly ever been examined. In addition, there is a summary of an historical case study, the discovery of the human intermaxillary bone by Goethe and of the specialists' reactions on this discovery, especially that of Soemmerring.     

Umm an‐Nar burial 401 at Bat,Oman: architecture and finds

The archaeological site at Bat has an important status with regard to research on the Umm an‐Nar culture. Investigations began there in 1972 and were revived in 2004, when the excavation of tomb 401 was begun. This paper presents the complete corpus of grave‐goods. Despite all the disturbances within the find layers, when comparing the two chambers it is possible to observe some indications of the different burial cycles and detect distinguishing characteristics. Taking into account the divergent earlier and later ceramic styles, burial use must be proposed between 2400 and 2200 BC. This date accords with observations of the architectural details of tomb 401 and with the sequence of tomb construction types in the Bat region. This paper is dedicated to the memory of professor Gerd Weisgerber.     

The Community Structure of Research and Development Cooperation in Europe: Evidence from a Social Network Perspective

The focus of this article is on precompetitive research and development (R&D) cooperation across Europe, as captured by R&D joint ventures funded by the European Commission in the time period 1998–2002, within the Fifth Framework Programme. The cooperations in this program give rise to a bipartite network with 72,745 network edges between 25,839 actors (representing organizations that include firms, universities, research organizations, and public agencies) and 9,490 R&D projects. Participating actors are linked only through joint projects. In this article, we describe a community‐identification problem based on the concept of modularity, use the recently introduced label‐propagation algorithm to identify communities in the network and differentiate the identified communities by developing community‐specific profiles with social network analysis and geographic visualization techniques. We expect the results to enrich our picture of the European Research Area (ERA) by providing new insights into the global and local structures of R&D cooperation across Europe. Este artículo se centra en la cooperación en investigación precompetitiva y desarrollo (I + D) en toda Europa tal y como se manifiesta en iniciativas conjuntas de I + D financiadas por la Comisión Europea durante el periodo 1998–2002, dentro del Quinto Programa Marco (5PM). La cooperación en este programa dio lugar a una red bipartita con 72.745 conexiones entre los 25.839 agentes (representando organizaciones que incluyen empresas, universidades, organizaciones de investigación y organismos públicos), y 9.490 proyectos de I + D. Los agentes participantes están vinculados sólo a través de proyectos conjuntos. En este artículo describimos un problema de identificación comunitaria basado en el concepto de modularidad, usamos el recientemente introducido algoritmo de propagación de etiquetas, Label‐propagation Algorithm (LPA) para identificar las comunidades en la red, y diferenciamos las comunidades identificadas desarrollando perfiles específicos comunitarios mediante el análisis de redes sociales y técnicas de visualización geográfica. Esperamos que los resultados enriquezcan nuestra visión del Espacio Europeo de Investigación (European Research Area, ERA), aportando nuevas perspectivas sobre las estructuras globales y locales de cooperación en I + D en Europa. 本文关注1998–2002年间在第五框架计划（FP5）下由研究与发展联合基金支持的欧盟研发计划中的竞争前欧洲研发合作。该项目合作形成一个在25839个参与者（执行组织,包括企业,大学,研究机构级公共部门）和9490个项目间拥有72745条边的双向网络,参与者仅仅通过合作项目连接。本文描述了基于模块化的社团识别问题。利用最近发展的标签传递算法（LPA）对网络群体进行识别,利用社会网络分析和地理可视化方法构建了群体专属的描述,区分识别出不同研发群体的资料。希望上述结果可以提供欧洲范围内研发合作的全局和局部结构的新视角,从而丰富欧洲研究区（ERA）的图景。     

A Spatial Autoregressive Poisson Gravity Model

In this article, a Poisson gravity model is introduced that incorporates spatial dependence of the explained variable without relying on restrictive distributional assumptions of the underlying data‐generating process. The model comprises a spatially filtered component—including the origin‐, destination‐, and origin‐destination‐specific variables—and a spatial residual variable that captures origin‐ and destination‐based spatial autocorrelation. We derive a two‐stage nonlinear least‐squares (NLS) estimator (2NLS) that is hetero‐scedasticity‐robust and, thus, controls for the problem of over‐ or underdispersion that often is present in the empirical analysis of discrete data or, in the case of overdispersion, if spatial autocorrelation is present. This estimator can be shown to have desirable properties for different distributional assumptions, like the observed flows or (spatially) filtered component being either Poisson or negative binomial. In our spatial autoregressive (SAR) model specification, the resulting parameter estimates can be interpreted as the implied total impact effects defined as the sum of direct and indirect spatial feedback effects. Monte Carlo results indicate marginal finite sample biases in the mean and standard deviation of the parameter estimates and convergence to the true parameter values as the sample size increases. In addition, this article illustrates the model by analyzing patent citation flows data across European regions. En el presente artículo, se introduce un modelo de gravedad Poisson, que incorpora la dependencia espacial de la variable explicada, sin apoyarse en presunciones de distribución restrictivas del proceso subyacente de generación de datos. El modelo comprende de un componente espacialmente filtrado, que incluye las variables de origen, destino y origen‐destino específico; y una variable espacial residual que captura la auto‐correlación espacial basada en el origen y destino. Se deriva del calculador (2NLS) de dos etapas no lineales de mínimos cuadrados (NLS), el cual es robusto en heterocedasticidad, y por ello controla el problema de sobre‐dispersión o baja‐dispersión (over and under dispersion), que a menudo se presenta en el análisis empírico de datos discretos; o, en el caso de de sobre‐dispersión, cuando se presenta la auto correlación espacial. Este calculador puede demostrar tener propiedades deseables para diferentes supuestos distribucionales, como los flujos observados un componente (espacialmente) filtrado, ya sea Poisson o binomial negativo. En nuestra especificación de modelo espacial auto regresivo (SAR), las estimaciones de los parámetros resultantes se pueden interpretar como los efectos de impacto total implícitos, definidos como la suma de efectos espaciales, directos o indirectos, de retroalimentación (feedback). Los resultados Monte Carlo indican sesgos marginales de muestras finitas en la media y la desviación estándar de los parámetros estimados, y la convergencia de los valores de los parámetros reales, a medida que aumenta el tamaño de muestra. Este artículo ilustra el modelo mediante el análisis de flujos de datos de citas de patentes, a través de las regiones europeas. 本文提出了一种蕴含空间依赖的泊松引力模型,该模型中解释变量无需依赖潜在数据生成过程的限制性分布假设。该模型由包含起点、终点、起点‐终点特定变量的空间滤波组分和空间残差变量组成,能捕捉到基于起点和终点的空间自相关。我们推导出一个二阶非线性最小二乘（NLS）估计（2NLS）,它对异方差具有鲁棒性,从而可控制对于离散或过离散数据经验性分析中经常出现的过离散和低离散问题。如果空间自相关存在,过离散数据分析就是一个例子。对于不同的分布假设,如或泊松分布或是负二项式分布的观测流或（空间）滤波组分,该估计量显示出令人满意的性能。在本文的空间自回归（SAR）模型设定中,参数估计结果可解释为隐含的全局影响效应,并可被定义为直接和间接的空间反馈效应之和。蒙特卡罗结果给出了参数估计中均值、标准差的临界有限样本偏差,且随样本量增大收敛于真正参数值。此外,本文基于欧洲地区专利引用的流数据进行了模型验证。