Spatial Autoregressive Model Research Articles

Financial development, institutions, and economic growth nexus: A spatial econometrics analysis using geographical and institutional proximities

AbstractThis paper investigates the nexus between financial development (FD), institutions, and economic growth using a spatial autoregressive model on a panel dataset of 82 countries from 1990 to 2019. We measure the dependence between countries through geographical and institutional proximity. The latter has not been widely explored in the finance‐growth literature. The concept of institutional proximity proposes that countries with similar institutions will have similar levels of economic growth and larger spillovers once spatial effects of FD and institutional quality are controlled. Overall, our findings support this proposition, as FD and political institutions are shown to have significant positive effects on growth. However, the growth‐effect of FD becomes negative beyond a certain threshold. We also find significant positive spatial lag growth in the model, indicating the presence of indirect spillover effects of FD and institutions on the growth of neighbouring countries in both geographical and institutional spheres. Furthermore, the spatial growth model with the institutional proximity matrix exhibits a higher rate of convergence and larger size of spillover than the model with geographical proximity. These findings are robust to various model specifications, and the paper concludes with some policy recommendations.

A Bayesian Variable Selection Method for Spatial Autoregressive Quantile Models

In this paper, a Bayesian variable selection method for spatial autoregressive (SAR) quantile models is proposed on the basis of spike and slab prior for regression parameters. The SAR quantile models, which are more generalized than SAR models and quantile regression models, are specified by adopting the asymmetric Laplace distribution for the error term in the classical SAR models. The proposed approach could perform simultaneously robust parametric estimation and variable selection in the context of SAR quantile models. Bayesian statistical inferences are implemented by a detailed Markov chain Monte Carlo (MCMC) procedure that combines Gibbs samplers with a probability integral transformation (PIT) algorithm. In the end, empirical numerical examples including several simulation studies and a Boston housing price data analysis are employed to demonstrate the newly developed methodologies.

Research on the Impact of Atmospheric Self-Purification Capacity on Environmental Pollution: Based on the Threshold Effect of Environmental Regulation

In China, Hebei Province and Guangdong Province have many pollution-intensive industries; yet Hebei suffers more serious atmospheric or environmental pollution than Guangdong. To explain the phenomenon, this paper chooses the statistical data of 286 prefecture-level cities in the Chinese mainland from 2005 to 2018 and empirically tests the spatial effect and threshold characteristics of atmospheric self-purification capacity on environmental pollution by using the spatial autoregression model (SAR), spatial Durbin model (SDM), and panel threshold model. As evinced, the local atmospheric self-purification capacity has a significant inhibitory effect on environmental pollution, and the absolute value of the direct effect coefficient reaches 1.337. Simultaneously, atmospheric self-purification capacity has a threshold effect on environmental pollution. The threshold value of environmental regulation as a threshold variable is 11.6349. This means that when the level of environmental regulation proves higher than 11.6349, it attenuates the inhibitory effect of the atmospheric self-purification capacity on environmental pollution. As the heterogeneity research unveils, atmospheric self-purification capacities in various regions form a significant correlation with environmental pollution. This paper suggests that local governments should strengthen environmental regulation and construct an inter-regional joint prevention and control system for atmospheric-pollution governance to enhance the atmospheric self-purification capacity.

Analysis of wildfires and their extremes via spatial quantile autoregressive model

Analysis of wildfires and their extremes via spatial quantile autoregressive model

CONSISTENT NON-GAUSSIAN PSEUDO MAXIMUM LIKELIHOOD ESTIMATORS OF SPATIAL AUTOREGRESSIVE MODELS

This paper studies the non-Gaussian pseudo maximum likelihood (PML) estimation of a spatial autoregressive (SAR) model with SAR disturbances. If the spatial weights matrix $M_{n}$ for the SAR disturbances is normalized to have row sums equal to 1 or the model reduces to a SAR model with no SAR process of disturbances, the non-Gaussian PML estimator (NGPMLE) for model parameters except the intercept term and the variance $\sigma _{0}^{2}$ of independent and identically distributed (i.i.d.) innovations in the model is consistent. Without row normalization of $M_{n}$ , the symmetry of i.i.d. innovations leads to consistent NGPMLE for model parameters except $\sigma _{0}^{2}$ . With neither row normalization of $M_{n}$ nor the symmetry of innovations, a location parameter can be added to the non-Gaussian pseudo likelihood function to achieve consistent estimation of model parameters except $\sigma _{0}^{2}$ . The NGPMLE with no added parameter can have a significant efficiency improvement upon the Gaussian PML estimator and the generalized method of moments estimator based on linear and quadratic moments. We also propose a non-Gaussian score test for spatial dependence, which can be locally more powerful than the Gaussian score test. Monte Carlo results show that our NGPMLE with no added parameter and the score test based on it perform well in finite samples.

Determinants of Pneumonia mortality in Bogota, Colombia: A spatial econometrics approach

Bogota, the capital and largest city of Colombia, constantly fights against easily transmitted and endemic–epidemic diseases that lead to enormous public health problems. Pneumonia is currently the leading cause of mortality attributable respiratory infections in the city. Its recurrence and impact have been partially explained by biological, medical, and behavioural factors. Against this background, this study investigates Pneumonia mortality rates in Bogota from 2004 and 2014. We identified a set of environmental, socioeconomic, behavioural, and medical care factors whose interaction in space could explain the occurrence and impact of the disease in the Iberoamerican city. We adopted a spatial autoregressive models framework to study the spatial dependence and heterogeneity of Pneumonia mortality rates associated with well-known risk factors. The results highlight the different types of spatial processes governing Pneumonia mortality. Furthermore, they demonstrate and quantify the driving factors that stimulate the spatial spread and clustering of mortality rates. Our study stresses the importance of spatial modelling of context-dependent diseases such as Pneumonia. Likewise, we emphasize the need to develop comprehensive public health policies that consider the space and contextual factors.

Green technologies, interdependencies, and policy

The present study explores the technological interdependencies between green and non-green inventions. First, we look at whether inventive activities in environmentally-friendly domains depend on patenting in related technological domains that are not green. Based on patent data filed over the 1978–2014 period, we estimate a spatial autoregressive model using co-occurrence matrices to capture technological interdependencies. Our first finding highlights that the development of green technologies strongly relies on advances in other green and in particular non-green technological domains, whose relevance for the green economy is usually neglected. Building on this insight, we detect the non-green interdependent technologies that co-occur with green ones and assess whether environmental policies affect this particular instantiation of technologies at the country level. The results of the instrumental variable approach confirm that while environmental policies spur green patenting, they do not displace the development of the non-green technological pillars upon which green inventions develop. However, at the same time, environmental policies do not enhance patenting in non-green interdependent technologies which would speed-up the transition towards sustainable economies.

GMM estimation of partially linear additive spatial autoregressive model

This paper focuses on studying the estimation method of partially linear additive spatial autoregressive model (PLASARM) by combining both parametric and nonparametric terms. With the nonparametric functions approximated by local linear estimator, the generalized method of moment (GMM) estimators is proposed. The large sample properties of the estimators are derived for the case with a single nonparametric term and extended to an arbitrary number of nonparametric additive terms under some mild conditions. The small sample performance for our estimators is assessed by Monte Carlo simulation. In addition, the proposed method is used to analyze the forces of Chinese housing price.

Pemodelan Pertumbuhan E-Commerce di Indonesia dengan Spatial Autoregresive Model (SAR)

The development of information technology has had a significant impact on the growth of e-commerce in Indonesia. However, the distribution of e-commerce is still concentrated in Java and Sumatera. It shows the inequality of the distribution of the e-commerce industry. Therefore, this study attempted to model the growth of e-commerce by considering the effect of dependence between regions. The variables use in this study included economic growth, base transceiver station (BTS), computer use, cellular phone ownership and the availability of strong signals (4G). The methods used were the Spatial Autoregressive Model (SAR) and the Spatial Error Model (SEM). The study's results showed that the SAR model was better than the SEM model. In addition, the test results indicated an autocorrelation relationship between provinces, which means that the growth of e-commerce in a province will be followed by an increase in e-commerce in the surrounding region. Meanwhile, the e-commerce growth in a province was affected by BTS, computer and telephone use, the availability of strong signals, and spatial residuals from other provinces that are close to each other.

Estimating flow data models of international trade: dual gravity and spatial interactions

This article investigates asymptotic properties of quasi-maximum likelihood (QML) estimates for flow data on the dual gravity model in international trade with spatial interactions (dependence). The dual gravity model has a well-established economic foundation, and it takes the form of a spatial autoregressive (SAR) model. The dual gravity model originates from Behrens et al., but the spatial weights matrix motivated by their economic theory has a feature that violates existing regularity conditions for asymptotic econometrics analysis. By overcoming the limitations of existing asymptotic theory, we show that QML estimates are consistent and asymptotically normal. The simulation results show the satisfactory finite sample performance of the estimates. We illustrate the usefulness of the model by investigating the McCallum “border puzzle” in the gravity literature.

Indirect inference estimation of higher-order spatial autoregressive models

This paper proposes estimating parameters in higher-order spatial autoregressive models, where the error term also follows a spatial autoregression and its innovations are heteroskedastic, by matching the simple ordinary least squares estimator with its analytical approximate expectation, following the principle of indirect inference. The resulting estimator is shown to be consistent, asymptotically normal, simulation-free, and robust to unknown heteroskedasticity. Monte Carlo simulations demonstrate its good finite-sample properties in comparison with existing estimators. An empirical study of Airbnb rental prices in the city of Asheville illustrates that the structure of spatial correlation and effects of various factors at the early stage of the COVID-19 pandemic are quite different from those during the second summer. Notably, during the pandemic, safety is valued more and on-line reviews are valued much less.

Are riskier cities more compact? An empirical study of the 11 largest census metropolitan areas in Canada, 2016

AbstractWhy are some cities more compact than others? We argue that riskier housing markets have a costlier real option; developers would require greater compensation to build now—thus, developers are being incentivized to delay, giving rise to more compact cities. We test this hypothesis cross‐sectionally for Canada's 11 largest census metropolitan areas. We interpret satellite imageries and estimate a hierarchical spatial autoregressive model to account for both the hierarchical and the spatial structure of our data. Our results show that, on average, a one‐percentage‐point increase in price risk reduces urban land coverage in the fringe by about 0.7 percentage point.

Spatial autoregressions with an extended parameter space and similarity-based weights

We provide in this paper asymptotic theory for a spatial autoregressive model (SAR, henceforth) in which the spatial coefficient, λ, is allowed to be less than or equal to unity, as well as consistent with a local to unit root (LUR) model and of the moderate integration (MI) from unity type, and the spatial weights are allowed to be similarity-based and data driven. Other special cases of our setting include the random walk, a model in which all the weights are equal, the standard SAR model in which λ<1 and the similarity based autoregression in which λ=1 and data do not display a natural order. As the norming rates for the asymptotic theory are very different in the λ<1 - compared with the λ=1 and LUR cases, we resort to random norming that treats all cases in a uniform manner. It turns out that standard CLT results prevail in a large class of models in which the infinity norm of the inverse of the weighting structure that characterizes the reduced-form process is Onγ , γ∈[0,1), and is non-standard in the case γ=1. We use a shifted profile likelihood to obtain results which are valid for all cases. A small simulation experiment supports our findings and the usefulness of our model is illustrated with an empirical application of the Boston housing data set in which the estimate of λ appeared to be very close to unity.

Deaths during the first year of the COVID-19 pandemic: insights from regional patterns in Germany and Poland

BackgroundGiven the nature of the spread of SARS-CoV-2, strong regional patterns in the fatal consequences of the COVID-19 pandemic related to local characteristics such as population and health care infrastructures were to be expected. In this paper we conduct a detailed examination of the spatial correlation of deaths in the first year of the pandemic in two neighbouring countries – Germany and Poland, which, among high income countries, seem particularly different in terms of the death toll associated with the COVID-19 pandemic. The analysis aims to yield evidence that spatial patterns of mortality can provide important clues as to the reasons behind significant differences in the consequences of the COVID-19 pandemic in these two countries.MethodsBased on official health and population statistics on the level of counties, we explore the spatial nature of mortality in 2020 in the two countries – which, as we show, reflects important contextual differences. We investigate three different measures of deaths: the officially recorded COVID-19 deaths, the total values of excessive deaths and the difference between the two. We link them to important pre-pandemic regional characteristics such as population, health care and economic conditions in multivariate spatial autoregressive models. From the point of view of pandemic related fatalities we stress the distinction between direct and indirect consequences of COVID-19, separating the latter further into two types, the spatial nature of which is likely to differ.ResultsThe COVID-19 pandemic led to much more excess deaths in Poland than in Germany. Detailed spatial analysis of deaths at the regional level shows a consistent pattern of deaths officially registered as related to COVID-19. For excess deaths, however, we find strong spatial correlation in Germany but little such evidence in Poland.ConclusionsIn contrast to Germany, for Poland we do not observe the expected spatial pattern of total excess deaths and the excess deaths over and above the official COVID-19 deaths. This difference cannot be explained by pre-pandemic regional factors such as economic and population structures or by healthcare infrastructure. The findings point to the need for alternative explanations related to the Polish policy reaction to the pandemic and failures in the areas of healthcare and public health, which resulted in a massive loss of life.

Evaluating the impact of different spatial linkages on forum outcome interdependencies in polycentric systems

AbstractIn complex polycentric systems, decisions regarding the governance of certain subsystems (e.g., watersheds) are often determined by networks of diverse actors who participate across a range of forums tackling interconnected collective actions issues (e.g., water quality, biodiversity, flood management). Compounding this structural complexity are the multifaceted interdependencies that exist between forums across a system. Drawing on the Ecology of Games Theory (EGT), this article investigates the impact of different types of network linkages on outcome interdependence between forums. Using a series of spatial autoregressive models on data collected in a Tampa Bay water governance system, I find evidence that co‐membership and organizational networks serve as pathways for outcome spillovers between forums. Building theory that helps elucidate how different types of network relationships may influence outcomes across a system is critical for the continued development of EGT and the governance of polycentric systems.

Peer effects drive non-conformance between built-up land expansion and zoning: Evidence from Zhangzhou city, China

Rapid expansion of built-up land is widespread and often does not follow established zoning regulations. This non-conforming expansion of built-up land may exacerbate social and environmental problems and has emerged as an important sustainability concern. In this study, we first evaluated the non-conforming expansion of built-up land to zoning in Zhangzhou City, China from 2010 to 2020. Non-conforming expansion of built-up land accounted for 67.61% of the newly developed built-up land area. These non-conformances mainly were edge expansion, via conversions from arable land and forest to industrial/mining/transportation land. We then used spatial autoregressive models to estimate five types of peer effects on non-conforming built-up land expansion among local governments. The geographical, political, economic, geographical-economic, and political-economic peer effects significantly increased the expansion area of non-conforming built-up land among 307 villages. Our findings improve our understanding, from the perspective of inter-governmental interactions, of why the extent of built-up land often was beyond the permitted limits of zoning regulations. Our research also has policy implications and suggests constraining the peer effects of local government land-use behaviors that violate zoning regulations. We recommend the establishment of closer interdisciplinary collaborations between spatial planning and land-system science to address non-conforming land-use changes.

Accommodation of outliers by robust MML estimation for spatial autoregressive model

Accommodation of outliers by robust MML estimation for spatial autoregressive model

Research on the Spatial Effects of Green Process Innovation, Environmental Regulation, and Precipitation on Environmental Air Pollution

In recent years, air pollution events have occurred frequently in China and have had serious impacts on people’s work and life. The research objective of the article is to find out the spatial effects of green process innovation, environmental regulation, rainfall, and pollution from industrial development on air pollution by compiling a development index of the air pollution industry and constructing spatial autoregression and spatial Durbin models. The study found that green technology innovation significantly reduced sulfur dioxide emissions and fog haze pollution. The development of industrial air pollution is an important source of sulfur dioxide and pollutant haze and has significant spatial spillover effects. The strengthening of environmental regulations leads to a decrease in life pollution but causes a transfer of industrial pollution. Rainfall is conducive to reducing the concentrations of pollutants in the air, such as those from chimneys and smog. Policy recommendations are proposed, such as establishing different environmental policies for different green technological innovations to promote green technology innovation; constructing a joint defense control system for regional air pollution; increasing the construction of artificial wetlands in areas with serious air pollution; and creating scientific plans to coordinate the development of industry, technology, and the environment, to provide help for China to reduce the emission of atmospheric environmental pollutants.

The Price Premium in Green Buildings: A Spatial Autoregressive Model and a Multi-Criteria Optimization Approach

The energy issue has given rise to a prolific research field, which branches into several strands. One of these strands focuses on the role played by building energy features in shaping property prices. Indeed, market players are expected to show a higher willingness to pay for building units characterized by higher energy performance. The study of the so-called price premium for building energy efficiency has flourished in the last decade or so; plenty of evidence is now available concerning its occurrence, although its magnitude is still debated. The literature relies on the methodological frameworks of statistical modeling and multiple regression, primarily employing hedonic price models. Lately, spatial autoregressive models have also been adopted. Here, we propose to deal with estimation of the price premium by adopting an innovative perspective. In particular, we use a methodological framework in which regression models are complemented with a multi-criteria optimization approach. Using a spatial autoregressive model first, and with D as the reference energy rating band, we find the following price premiums: 55% for A4, 42% for A3 to A, 20% for B or C, −14% for F, and −29% for G. The multi-criteria optimization approach proves efficient in estimating the price premium. The estimates above are essentially confirmed: the results converge for all the energy rating bands except for G.

Comparison of Spatial Weight Matrices in Spatial Autoregressive Model: Case Study of Intangible Cultural Heritage in Indonesia

Intangible Cultural Heritage (ICH) can effectively contribute to Sustainable Development Goals (SDGs) in all economic, social, and environmental dimensions, along with peace and security. Studying ICH in Indonesia cannot be separated from the spatial aspect of how an area's attributes are related to other areas located close to each other. Spatial regression modeling needs to be done by considering the selection of spatial weight matrix. Using the wrong spatial weight matrix will increase the standard error in parameter estimation. Therefore, this study aims to determine: the best spatial weight matrix to accommodate the spatial autocorrelation in analyzing the description of the spread of ICH in Indonesia; and the variables that are thought to influence the number of ICH determination in Indonesia. The spatial regression modeling used in this study is the Spatial Autoregressive (SAR) model and the spatial weight matrices compared in this study are queen contiguity and inverse distance. The best model is the SAR model used the queen contiguity spatial weight matrix because it has minimum values of AIC, BIC, RMSE and MAPE which are 310.397, 319.555, 18.857 and 57.169 respectively. Simultaneously, involved in performing arts, wearing traditional dress, knowing Indonesian folklore and the spatial lag contribute significantly to number of ICH determination in Indonesia. Partially, only knowing Indonesian folklore have a significant effect on number of ICH determination in Indonesia at significance level α=5%. Each additional 1% of population that knowing Indonesian folklore in an area increases number of ICH determination in that area by 0.6719 units .