Dynamic Spatial Panel Model Research Articles

Dynamiczno‑przestrzenna analiza zjawiska przenoszenia zmienności między rynkami reprezentującymi różne klasy aktywów z uwzględnieniem zmian cen ropy naftowej w latach 2000–2015

W obliczu licznych turbulencji na globalnym rynku finansowym wzrasta potrzeba głębszego przyjrzenia się zjawisku przenoszenia zmienności, gdyż w jego konsekwencji wzrost zmienności na jednym rynku może prowadzić do pojawienia się podwyższonej zmienności na innym. W przypadku tych zależności istotne wydają się zwłaszcza przesunięcia przestrzenne przejawiające się w reakcjach danego rynku w jednym kraju na zmiany dokonujące się na tym rynku w innych krajach. W podejściu tym analizy przeprowadza się przy założeniu, że rynki są zlokalizowane w przestrzeni metrycznej, gdzie zależności między zmiennymi opisującymi te rynki są funkcjami fizycznej lub częściej ekonomicznej odległości między nimi. Celem artykułu jest sprawdzenie, czy w kontekście zjawiska przenoszenia zmienności między rynkami poszczególnych klas aktywów dochodzi do ujawnienia się pewnych związków przestrzennych między nimi. Identyfikacji ewentualnych zależności przestrzennych dokonano z wykorzystaniem dynamicznych panelowych modeli przestrzennych. Analizie poddano rynki akcji oraz dziesięcioletnich obligacji skarbowych reprezentujące wybrane kraje europejskie. Zakres czasowy badania objął lata 2000–2015.

The effects of gun control on crimes: a spatial interactive fixed effects approach

This paper examines the effect of right-to-carry laws on crimes. We relax the assumption that unobserved time effects have homogeneous impacts on states; therefore, states with right-to-carry laws may follow different time trends which might be stronger or weaker than those of other states including states with no right-to-carry laws. The heterogeneous time trends are modeled by a factor structure where time factors represent time-varying unobservables, and factor loadings account for their heterogeneous impacts across states. No assumption is imposed on the shape of the time trend. Crime statistics exhibit spatial dependence, and a state’s adoption of right-to-carry law may have external effects on its neighboring states. Using a dynamic spatial panel model with interactive effects, we find positive spatial spillovers in crime rates. Depending on a crime category, an average $$1\%$$ reduction in crime rates in neighboring states can decrease crime rates by 0.069–0.287%, with property crimes exhibiting higher degrees of spatial dependence than violent crimes. We find that although the passage of right-to-carry laws has no significant effects on the overall violent or property crime rates, they lead to short-term increases in robbery and medium-term decreases in murder rates. The results are robust to the number of factors, a different sample ending point, and some alternative spatial weights matrices and model specifications.

US Metropolitan Area Resilience: Insights from dynamic spatial panel estimation

In this paper, we show that the economic crisis commencing in 2007 had different impacts across US Metropolitan Statistical Areas, and seek to understand why differences occurred. The hypothesis of interest is that differences in industrial structure are a cause of variations in response to the crisis. Our approach uses a state-of-the art dynamic spatial panel model to obtain counterfactual predictions of Metropolitan Statistical Area employment levels from 2008 to 2014. The counterfactual employment series are compared with actual employment paths in order to obtain Metropolitan Statistical Area-specific measures of crisis impact, which then are analysed with a view to testing the hypothesis that resilience to the crisis was dependent on Metropolitan Statistical Area industrial structure.

Identifying the spatial effects and driving factors of urban PM2.5 pollution in China

Exploring exactly where air pollution comes from, and identifying the key factors that influence it, can provide a scientific basis for the rational formulation and effective implementation of air pollution policies in China. Based on the data from 2001 to 2012 covering PM2.5 concentrations in 285 Chinese cities, we use dynamic spatial panel models to empirically analyze the key driving factors of this air pollution. Results show that China’s urban smog demonstrates both obvious global spatial autocorrelation and local spatial agglomeration. There is a significant inverted “U-shaped” curve between economic development level and air pollution, and most cities are in the phase in which pollution is increasing in conjunction with improvements to the economy. Due to a rapid increase in population in built up areas, a high-proportion of secondary industry, a coal-dominated energy structure and increasing traffic intensity, China’s smog problem is becoming more and more serious. FDI probably will not play a future role in mitigating the air pollution. Central heating in winter in northern China further aggravates local smog to a certain extent. Because China’s haze pollution presents path-dependent characteristics and spatial spillover effects in the time dimension and in the space dimension respectively, so smog alleviation policies should be implemented based both on the strategies of maximizing effort and regional joint prevention and control.

Dynamic spatial panel estimates of war contagion

AbstractWe estimate the temporal, spatial and “spatio‐temporal” effects of war using a dynamic spatial panel model. Our argument is that it is important to account for both the space and temporal lags concurrently, while instead the existing literature largely tends to focus on one or the other. Key findings are as follows: first, there is evidence that both temporal and spatial effects significantly impact upon the duration of war. Second, we also find that the combined “spatio‐temporal” interaction effect is significant only when excluding contemporaneous spatial lag effect. Third, while stronger for high‐intensity conflict, spatial and temporal effects remain significant also for low‐intensity conflict. Fourth, the spatial effect is stronger in magnitude for interstate wars. Our results point to the importance of regional co‐operation for conflict prevention and peace stabilisation.

The emissions reduction effect and technical progress effect of environmental regulation policy tools

How to set out the provisions that ensure emissions reduction and technical progress in environmental regulation is very important for both China’s future emissions reduction and sustainable development. The paper uses statistical data from 30 Chinese provinces from 1997 to 2014 and empirically tests the effects of different types of environmental policies and regulations on emissions reduction and technical progress by using dynamic spatial panel models. The results of spatial autocorrelation tests show that there are both significant positive global autocorrelation and local spatial agglomeration effects relating to pollutant emissions and technical progress. Dynamic spatial panel models indicate that command and control regulations (CCR) are conducive to emissions reduction, but their effects on technical progress are not significant. Market based regulations (MBR) are conducive to technical progress, but their effects on the reduction of emissions are relatively weak. There is a significant inverted-U relationship between economic development level and carbon emissions, validating the EKC hypothesis in China, but the effects of foreign direct investment on carbon reduction and technical progress are not significant. The paper recommends that China should optimize a combination of environmental regulations so as to achieve the win-win outcome of both emissions reduction and technical progress.

Entrepreneurial Spillovers Over Space and Time

Entrepreneurship is a local and dynamic phenomenon. We jointly investigate spatial spillovers and time persistence of regional new business formation. Using panel data from all 402 German counties for 1996-2011, we estimate dynamic spatial panel models of business creation in the high-tech and manufacturing industries. We consider regions of different sizes and systematically search for the most suitable spatial weighting matrices. We find substantial spatial spillovers as well as time persistence of start-up activity, especially in the high-tech industry. This indicates that entrepreneurship is deeply rooted in regions and underlines the importance of local entrepreneurship culture for new business formation.

Domestic transport effects on regional export trade in Greece

This paper examines the role of domestic transport on regional export trade in Greece. It aims to understand how changes in the transport conditions of a region can affect its own and neighboring regions' ability to improve foreign trade. The proposed dynamic spatial panel model extends previous ones in the scant related literature, by accounting for spillover effects and own time lagged responses of export flows to changes in variables related, among others, to network distance and accessibility. The results suggest a considerable number of indirect (spatially lagged) effects that are significant for the regional export trade, including those of highway corridors. Agglomeration economies positively affect manufacturing exports by ship and truck in the own prefecture, while manufacturing specialization has a significant impact on maritime transport. It is also shown that failure to account for long-run responses can significantly underestimate the effect of changes in the distance to major transport facilities on export volume. Especially the enhancement of interregional accessibility and market potential has a major impact on the agricultural exports by road. The findings have implications for the coordination of regional investment policies and the planning of the mainland transport system in connection with the location of logistics hubs.

Sugarcane industry's socioeconomic impact in São Paulo, Brazil: A spatial dynamic panel approach

This study assesses the socioeconomic development impacts of the recent sugarcane industry expansion on municipalities in the Brazilian state of São Paulo over seven years, from 2005 through 2011. It was used as socioeconomic development indicator the Index of Municipal Development (IFDM), provided by the Federation of the State of Rio de Janeiro Industries (FIRJAN). A dynamic spatial panel model was built using the System Generalized Method of Moments (GMM-SYS) to assess the impacts of the sugarcane industry, caused by the expansion of both the cultivated area and the presence of ethanol and sugar processing plants. We found that the presence of a processing plant has a positive effect in the socioeconomic development of the municipality where the plant is located and in neighboring municipalities. Besides, we found a small negative relationship between increases in the amount of area devoted to sugarcane cultivation in a municipality and the IFDM value for that municipality, which can be explained by job losses in the farming sector, most likely by the recent mechanization process of sugarcane harvesting.

The W Matrix in Network and Spatial Econometrics: Issues Relating to Specification and Estimation

Network and spatial econometric models commonly embody a so-called W matrix which defines the connectivity between nodes of a network. The reason for the existence of W is that it facilitates parsimonious parametrization of inter-nodal interaction which would otherwise be very difficult to achieve from a practical modelling perspective. The problem considered in this paper is the effect of misspecifying W. The paper demonstrates the effect in the context of two types of model, the dynamic spatial autoregressive panel model and the multilevel spatial autoregressive panel model, both of which include W as part of the model specification and use W in estimation. Monte Carlo results are presented showing the impact on bias and RMSE of misspecification of W. The paper highlights the need for careful attention to the correct structure of W in spatial econometric and network modelling.

Spatial Linkages in Listed Property Returns in Tranquil and Distressed Periods

Executive Summary. In this study, we use a dynamic spatial panel model to assess the degree of cross-country co-movement of the returns of listed property companies caused by economic, financial, and geographic closeness. We find that the asset-side exposure of banks best captures the comovements in returns and presents a channel of credit risk transmission across countries. During the Global Financial Crisis, asset-side bank exposure and foreign direct investment linkages contribute to a significant increase in the comovement of the returns of listed property companies through which liquidity and credit risk shocks may have been transmitted to asset prices internationally.

The regional economic impact of oil and gas extraction in Texas

This paper empirically investigates the regional economic impact of oil and gas extraction in Texas during the recent shale oil boom. Regressions with county-level data over the period 2009–2014 support smaller multiplier effects on local employment and income than corresponding estimates drawn from popular input–output-based studies. Economic impacts were larger for extraction from gas wells than oil wells, while the drilling phase generated comparable impacts. Estimates of economic impacts are greater in a dynamic spatial panel model that allows for spillover effects across local economies as well as over time.

Regional Migration, Growth and Convergence – A Spatial Dynamic Panel Model of Germany

Kubis A. and Schneider L. Regional migration, growth and convergence – a spatial dynamic panel model of Germany, Regional Studies. This paper empirically analyses the question of how regional migration affects regional convergence and growth in post-reunification Germany. Addressing the endogeneity of migration and human capital, a dynamic panel data model within the framework of β-convergence is applied, accounting for spatial effects. The regressions indicate that out-migration has a negative but modest effect on regional growth; the expected effect of skill selection is only partly confirmed. In the East German subsample, in-migration increases growth independently of its human capital effect; in West Germany, in-migration lowers growth per se, but this negative impact is offset by the growth-stimulating forces of migrants’ skills.

Bank integration and co-movements across housing markets

This paper investigates whether bank integration measured by cross-border bank flows can capture the co-movements across housing markets in developed countries by using a spatial dynamic panel model. The transmission can occur through a global banking channel in which global banks intermediate wholesale funding to local banks. Changes in financial conditions are passed across borders through the banks’ balance-sheet exposure to credit, currency, maturity, and funding risks resulting in house price spillovers. While controlling for country-level and global factors, we find significant co-movement across housing markets of countries with proportionally high bank integration. Bank integration can better capture house price co-movements than other measures of economic integration. Once we account for bank exposure, other spatial linkages traditionally used to account for return co-movements across region – such as trade, foreign direct investment, portfolio investment, geographic proximity, etc. – become insignificant. Moreover, we find that the co-movement across housing markets decreases for countries with less developed mortgage markets characterized by fixed mortgage rate contracts, low limits of loan-to-value ratios and no mortgage equity withdrawal.

Spatial panel data forecasting over different horizons, cross-sectional and temporal dimensions

Les évaluations empiriques de la capacité de prévision des modèles spatiaux en panel sont encore peu nombreuses. Quelques contributions méthodologiques reposent sur des données simulées afin de mettre en avant le potentiel de ces méthodes. Tandis que les simulations peuvent être utiles pour évaluer les propriétés d’un seul estimateur, le cadre empirique des études de simulation est souvent basé sur des hypothèses fortes concernant la forme et la régularité de la distribution statistique des variables utilisées. Il est alors utile d’avoir, à côté des études de simulation, des évaluations empiriques des modèles économétriques concurrents basées sur des données réelles. Dans cet article, nous évaluons des méthodes spatiales (dynamiques) en panel concurrentes, en utilisant un certain nombre de bases de données caractérisées par différentes dimensions temporelles et coupes transversales, ainsi que différents niveaux d’autocorrélation spatiale. Nous réalisons notre étude empirique sur des données de chômage régional pour la France, l’Espagne et la Suisse. En outre, nous faisons des tests sur différents horizons de prévision, afin d’évaluer la vitesse de dégradation de la qualité de prévision. Nous comparons deux classes de méthodes: les modèles Var spatiaux (Sp Var ) et les modèles dynamiques en panel utilisant des vecteurs propres de filtrage spatial ( Sf ). Nous constatons que, comme l’on pouvait s’y attendre, le déséquilibre entre la dimension temporelle et transversale (T > > n) joue en faveur du modèle Sp Var . Néanmoins l’avantage du modèle de Sp Var sur le modèle SF semble diminuer à mesure que l’horizon de prévision s’élargit et le modèle Sf semble être préféré pour des prévisions très lointaines.

Identification of Spatial Durbin Panel Models

SummaryThis paper considers identification of spatial Durbin dynamic panel models under 2SLS and ML estimations. We show that the parameters are generally identified via 2SLS moment relations or expected log‐likelihood or quasi‐likelihood functions. Monte Carlo experiments suggest that omitting relevant Durbin terms can result in significant biases in regression estimates, while including an irrelevant Durbin term causes no obvious loss of efficiency. Empirical illustration of the international spillover of economic growth through bilateral trade shows that inclusion of Durbin terms can be important. Copyright © 2015 John Wiley & Sons, Ltd.

Dynamic Spatial Panel Models: Networks, Common Shocks, and Sequential Exogeneity

This paper considers a class of GMM estimators for general dynamic panel models, allowing for cross sectional dependence due to spatial lags and due to unspecified common shocks. We significantly expand the scope of the existing literature by allowing for endogenous spatial weight matrices, time-varying interactive effects, as well as weakly exogenous covariates. The model is expected to be useful for empirical work in both macro and microeconomics. An important area of application is in social interaction and network models where our specification can accommodate data dependent network formation. We discuss explicit examples from the recent social interaction literature. Identification of spatial interaction parameters is achieved through a combination of linear and quadratic moment conditions. We develop an orthogonal forward differencing transformation to aid in the estimation of factor components while maintaining orthogonality of moment conditions. This is an important ingredient to a tractable asymptotic distribution of our estimators. In the social interactions example, orthogonal forward differencing amounts to controlling for unobserved correlated effects by combining multiple outcome measures.

Forecasting with dynamic spatial panel data: practical implementation methods

This paper addresses the issue of how in practice one might predict given that the data generating process is a dynamic spatial panel model. One period ahead predictions are calculated using various alternative predictors, some of which are misspecified, and their relative performance evaluated.

Internal and external effects of R&D subsidies and fiscal incentives: Empirical evidence using spatial dynamic panel models

Most studies evaluating the macroeconomic effects of financial support policies on business-funded R&D use econometric methods that do not consider the existence of spatial effects, and generate biased estimates. In this paper, we discus and address this problem using spatial dynamic panel data methods. This allow us to provide new insights on the internal (in-country) and external (out-of-country) effects of both Research and Development (R&D) subsidies and fiscal incentives. We use a database of 25 OECD countries for the period 1990–2009. In relation to internal effects, for both instruments, we find a non-linear relationship between their effect on private R&D and their level (suggesting the possibility of leveraging and crowding-out effects). We also find a substitution effect between the R&D subsidies and fiscal incentives implemented within a country. Concerning the spatial component, we find evidence of positive spatial spillovers among private R&D investments. However, our results suggest the existence of competition/substitution effects between national R&D policies.

The Spatial Effect Identification of Pollution Treatment Investment in China

Pollution treatment investment is an important part of environment protection in terms of energy saving and emission reduction. A dynamic spatial panel model is constructed in this paper, identifying the spatial effect in pollution treatment investment of regions and discussing the mutual influences among different regions. The result shows a mutual positive influence and behavioral convergence regarding to the pollution treatment investment behavior among regions.