Local and global spatial effects in hierarchical models

Hierarchical models have a long history in empirical applications; recognition of the fact that many datasets of interest to applied econometricians are nested; counties within states, pupils within school, regions within countries, etc. Just as many datasets are characterized by nesting, many are also characterized by the presence of spatial dependence or spatial heterogeneity. Significant advances have been made in developing econometric techniques and models to allow applied econometricians to address this spatial dimension to their data. This article fuses these two literatures together and combines a hierarchical model with the two general spatial econometric models.     

Human capital effects on labour productivity in EU regions

Recent years have seen a wealth of articles on spatial effects in empirical growth specifications. Endogenous growth models, together with the arguments of the new economic geography, have led to spatial dependence being identified with the existence of externalities which cross regional borders. This article continues in this line of research and offers new empirical evidence on the contribution of human capital and agglomeration economies to the differences in productivity in European Union regions. The article uses the spatial Durbin model with different weight matrices to explain the relation between human capital variables and labour productivity, with the advantage that it allows the effects of spatial externalities associated to human capital and agglomeration economies to be quantified.     

中国省域城市化水平影响因素的空间计量分析

运用空间计量方法对2005年中国31个省级单位城市化水平的影响因素进行了实证分析.研究结果一方面证实了中国地区城市化发展存在空间依赖性,即一个地区城市化水平的提高将通过空间溢出促进周边地区的城市化发展;另一方面,我们发现产业结构的变化,尤其是第三产业的发展是影响地区城市化水平的主要因素.地区经济发展水平的提高和对外开放程度的加深对地区城市化水平提高有积极的作用,而教育水平滞后和城乡收入差距的扩大对推动城市化进程有负面的影响.     

The information content of regional employment data for forecasting aggregate conditions

We consider whether disaggregated data enhance the efficiency of aggregate employment forecasts. We find that incorporating spatial interaction into a disaggregated forecasting model lowers the out-of-sample mean squared error from a univariate aggregate model by 70% at a two-year horizon.     

我国保险密度空间收敛的实证研究

文章运用空间计量方法分析了我国省际保险密度的空间相关性,发现我国省际保险密度在呈现出区域集聚特征的同时,全国趋同的趋势也在迅速增强.在运用三种空间经济计量模型研究了我国省际保险密度增长的收敛性后,发现空间误差模型是研究我国省际保险密度空间收敛性的合适模型,全国保险密度的收敛速度大约为1.5%.虽然加入WTO等对我国保险密度的区域集聚性与整体收敛性都带来了冲击,但整体收敛的趋势依然稳定,表明区域保险业发展水平会随着经济发展水平的趋同而趋同.     

British regional growth and sectoral trends: global and local spatial econometric approaches

This article looks beneath the surface of British sub-regional aggregate Gross Value Added (GVA) growth over the period 1995 to 2007, by examining how the differing growth dynamics of the secondary and services sectors have influenced the overall regional growth process. A spatial econometric analysis is undertaken which tests regional secondary and services real GVA per capita for absolute and conditional convergence at the NUTS 3 level. Both local and global spatial analysis techniques are utilized in order to gain a detailed insight into the growth process over the period 1995 to 2007.     

交通基础设施的溢出效应及其产业差异——基于空间计量的比较分析

文章利用1998-2008年中国省级面板数据,在模型中加入不同经济意义空间权重矩阵的基础上,分析了我国交通基础设施的空间溢出效应。研究发现,我国交通基础设施的空间溢出效应更多地通过经济联系发生作用。交通基础设施对第二产业的空间溢出大于对第三产业的空间溢出,基于产业结构的空间溢出大于基于市场规模的空间溢出。此外,我国铁路溢出效应存在边际报酬递增的特征,而公路溢出效应则呈现边际报酬递减的现象。     

外商投资、贸易开放度与中国财政支出结构

文章采用空间计量经济方法,利用空间和时间固定效应的空间自回归模型和空间误差模型,就外商直接投资、贸易开放度与我国地方政府公共支出结构之间的关系进行分析。得出以下结论:我国各省的地方财政总支出及其主要构成部分存在显著的空间相关性;外商直接投资限制了政府部门规模,降低了总支出水平及其主要构成部分的支出水平,支持效率假说的推断;贸易开放度扩张了政府部门规模,提高了总支出水平及其主要构成部分的支出水平,支持补偿假说的推断。     

我国城市化与城乡收入差距关系再检验

通过利用2000—2008年的省级面板数据,建立空间面板计量模型,分析了城市化对城乡收入差距的影响,研究结果表明,在报告期内城市化拉大了城乡收入差距,城市化每提高1个百分点,城乡居民收入差距就拉大0.39个百分点。同时研究发现城乡收入差距在空间上存在显著的正相关性。     

Spatial variations in the relationship between economic diversity and stability

Using US county-level data, we explore how economic diversity influenced economic stability over the period of the Great Recession. We find that higher diversity is associated with greater stability, but there are distinct spatial patterns and the relationship does not hold for much of the central part of the US.     

Effects of spatial density on veterinarian income: where are all of the veterinarians?

With increased numbers of veterinarians in the market, it is critical to understand how this increased competition affects income potential at multiple levels. This study presents an empirical approach that incorporates local and nonlocalised spatial competition of firms into one model. By analysing the market for veterinarians using a spatial weight matrix approach, we are able to quantify localized and nonlocalised competition which assists in defining relevant market areas for veterinarians. Specifically, increased density within their county and surrounding counties decreases veterinarian income. Thus, the potential market area for veterinarians is larger than the local/county market in which they practice. This is important for veterinarians when choosing a location to practice, as they must consider the competition and demand in local and non-local areas.     

中国人口出生性别比的空间计量分析

利用中国2000年人口普查数据中各省市的人口出生性别比数据,定量检验了经济、教育、医疗及计划生育政策等因素对人口出生性别比的影响。人口出生性别比在地理上存在集聚现象,空间地理因素对其影响显著;教育和医疗水平对出生性别比的直接影响较小,但它们会通过空间地理因素、经济和计划生育政策等因素间接影响出生性别比。计划生育政策对人口出生性别比的影响最显著。经济及医疗水平越高出生性别比越低,教育水平越高出生性别比越高,计划生育政策越宽松出生性别比越低。     

Empirical investigation of the agriculture–malnutrition nexus in Africa: Spatial clustering and spillover effects

Many studies have been conducted to examine the direct effect of agriculture on the prevalence of malnutrition; however, there is little solid evidence on spatial spillover effects and much less on the heterogeneous effects stemming from spatial differences in nutritional conditions. We make up this gap by using a dynamic spatial Durbin model to characterize the impact of agricultural productivity on malnutrition in Africa. Our results show that countries in Eastern Africa are more likely to suffer from severe malnutrition than other regions. We find evidence for convergence in agricultural productivity across countries with moderate and high prevalence of malnutrition as disparities in their agricultural productivity narrow down over the sample period. It appears that the negative effect of agriculture on malnutrition is more evident in countries where the prevalence of malnutrition is lower. This implies that agricultural development does not play a substantial role in reducing malnutrition in the worst affected areas. We also report that poor agricultural development can deteriorate the nutritional status among neighboring countries in the short term, consistent with the spatial-locking effect of agriculture.     

Spatial panel data analysis with feasible GLS techniques: An application to the Chinese real exchange rate

Recent panel data approaches stress the importance of the location interdependence. Little has been done in the Balassa-Samuelson literature accounting for spatial dependence in the panel data context that allows for spatial autocorrelation. By utilising the recently developed Kapoor et al. (2007) spatial panel feasible GLS methods, we find that the Balassa-Samuelson effect in the Chinese economy during 1985 until 2000 generally does not appear to hold. However, the black market exchange rate tends to be more compatible with the theory.     

A generalized method of moments estimator for a spatial model with moving average errors, with application to real estate prices

This paper proposes a new GMM estimator for spatial regression models with moving average errors. Monte Carlo results are given which suggest that the GMM estimates are consistent and robust to non-normality, and the Bootstrap method is suggested as a way of testing the significance of the moving average parameter. The estimator is applied in a model of English real estate prices, in which the concepts of displaced demand and displaced supply are introduced to derive the spatial lag of prices, and the moving average error process represents spatially autocorrelated unmodelled variables.      

Does economic growth and energy consumption drive environmental degradation in China’s 31 provinces? New evidence from a spatial econometric perspective

The panel data analysis points to economic and social factors contributing to NO_x, PM_2.5, PM₁₀, SO₂, and VOCs in China’s 31 provinces. The spatial correlation analysis using Global and Local Moran’s I values indicates the existence of a significant and positive spatial autocorrelation with respect to environment, economy and energy, and the high spatial correlation is evident in the eastern region, covering the northern part of Yangtze River Delta, Huaihai Economic Zone, and the lower reaches of the Yellow River Economic Belt. The empirical estimation is performed through spatial lag and spatial Durbin models. All emitted air pollutants in 31 provinces have significant spatial dependence and strong spillover effects. There is an inverted U-shaped relationship between emitted air pollutants (NO_x, PM₁₀, VOCs, and PM_2.5) and per capita GDP, which follows the EKC hypothesis. The relationship between SO₂ and per capita GDP does not follow the EKC hypothesis. There is a positive relationship between pollutant emissions and coal consumption, which is consistent with current studies for various countries like Canada, Denmark, UK and US and regions like New York State. However, the effects of science and technology investment on air pollutants are mostly positive, which is not as policy expected.     

县际竞争和公共教育财政资源配置——基于空间经济计量研究

根据Moran’s I检验发现,公共教育财政资源地区配置上存在显著空间自相关性,即邻近县之间在配置公共教育财政资源上会互相影响,存在策略性行动,表明县际竞争的存在。此外,县级竞争力强弱受到诸多因素的影响。人均GDP、第二产业劳动力人数、人均居住面积对县级人均教育经费总支出的影响是正面显著的,而少数民族人口比率的影响是负面显著,非农业人口比率的影响是倒U型关系,外省迁入人口和本地适龄人口的影响是非线性的。在估计方法上,空间误差模型比OLS模型要好。     

Financial inclusion: measurement,spatial effects and influencing factors

Using the index of financial inclusion and the World Bank Global Findex database, this study measures the level of financial inclusion across countries. The results reveal a geographical spatial aggregation distribution in which developed European and North American countries enjoy higher levels of financial inclusion than the less developed countries of Africa and most of Asia. Accordingly, our spatial analysis proves our hypothesis and reveals dependence and aggregation effects among countries. Then, we employ spatial econometric research to identify those factors significantly associated with financial inclusion. The results show that an individual’s income, education and use of communications equipment are important factors that explain the level of financial inclusion, while financial depth and banking health status are the main determinants. Building an inclusive financial system is an important means for most countries to achieve the Millennium Development Goals.     

城际政府公共投资策略互动行为及其形成机制——基于278个地级及以上城市数据的实证分析

文章基于2007年收支分类改革后新的预算科目和278个地级及以上城市的数据,运用SLM、SEM、Durbin和SAC空间计量模型以及ML估计和工具变量GMM估计方法,通过设定相邻、地表距离和最临近三种空间地理矩阵以及工业化水平、土地出让金收入占比、房地产投资占比、城市化水平和FDI五种经济变量空间矩阵,对当前城市政府间公共投资类财政支出的策略互动情况进行了评估与甄别。结果发现,城市政府在相邻地理位置上的显著互动———以策略互补为主,具有特定的外部性范围和变化轨迹,而工业禀赋型、"土地"财政型和FDI型策略互动的影响则具有同质性,且总体低于以外溢效应和标尺效应为主要源泉的地理空间位置上的策略互动水平。最后,文章对相应理论和政策含义进行了探讨。     

A class of spatial econometric methods in the empirical analysis of clusters of firms in the space

In this paper we aim at identifying stylized facts in order to suggest adequate models for the co-agglomeration of industries in space. We describe a class of spatial statistical methods for the empirical analysis of spatial clusters. The main innovation of the paper consists in considering clustering for bivariate (rather than univariate) distributions. This allows uncovering co-agglomeration and repulsion phenomena between the different sectors. Furthermore we present empirical evidence on the pair-wise intra-sectoral spatial distribution of patents in Italy in 1990s. We identify some distinctive joint patterns of location between different sectors and we propose some possible economic interpretations. A previous version of this paper was presented at the Workshop on Spatial Econometrics and Statistics, held in Rome 25–27 May 2006. We wish to thank the participants for the useful comments received. The comments received by two anonymous referees are also gratefully acknowledged. They improved substantially the quality of our work.