James P. Lesage

• Ph.D.
• Professor Emeritus at University of Toledo

We use parallel processing and improved algorithms to search for the weights given to two locational coordinates as well as three non-locational dimensions to find multidimensional neighbors (previous in time) to fit a multidimensional STAR model. We find that the improvements allow for quick specification searches. The effect of the improved speci...

Using a network approach that circumvents well-known challenges in estimating peer effects, we show that interactions with a firm’s geographic neighbors play a significant causal role in corporate investment behavior and a modest role in financial policies and firm performance. Moreover, these geography network effects are almost entirely driven by...

Spatial econometric models rely on the weight matrix W to specify dependence. However, formation of W involves scalings of rows and columns. We provide a closed-form for the similarity in results between the common eigenvalue and row-stochastic scalings.

Use of multiplicative interaction of explanatory variables has been a standard practice in the regression modeling literature, and estimation of the parameters of such a model in the case of spatial autoregressive (SAR) or spatial Durbin (SDM) models can be accomplished using existing software for spatial regression estimation. However, use of the...

We present a spatial econometrics framework for estimating peer effects in capital structure. This approach exploits the heterogeneous and intransitive nature of peer networks to identify economically informative structural coefficients. In models of leverage levels, we detect significant peer-effect leverage coefficients that are on the order of 0...

We explore the role of alternative types of connectivity between regions in knowledge production. Past literature has criticized exclusive focus on the role played by spatial proximity in knowledge production. We introduce a methodology that allows for simultaneous consideration of multiple dependence sets, based on a convex combination of multiple...

Faced with the problem that conventional multidimensional fixed effects models only focus on unobserved heterogeneity, but ignore any potential cross-sectional dependence due to network interactions, we introduce a model of trade flows between countries over time that allows for network dependence in flows, based on sociocultural connectivity struc...

There is a great deal of literature regarding use of nongeographically based connectivity matrices or combinations of geographic and non-geographic structures in spatial econometric models. We focus on convex combinations of weight matrices that result in a single weight matrix reflecting multiple types of connectivity, where coefficients from the...

Some of the most effective public programs used in Latin America to reduce poverty and inequality have been non-contributory cash transfers. We examine country-specific characteristics that lead countries to adopt these programs over time using a state-transition spatial probit panel data model that takes into account dependence between countries’...

A strategy for MCMC estimation of a family of models involving multiple simultaneous dependence parameters is set forth that is capable of producing rapid estimates for problems involving a large number of observations. Simultaneous dependence parameters arise when dependence exists between dependent variable observations, with spatial and cross-se...

The focus is on cross-sectional dependence in panel trade flow models. We propose alternative specifications for modeling time-invariant factors such as sociocultural indicator variables, e.g., common language and currency. These are typically treated as a source of heterogeneity that is eliminated using fixed effects transformations, but we find e...

Bayesian vector autoregressions that allow for non-Gaussian, heteroscedastic and time-dependent disturbance structures for models involving a large number of variables have been recently introduced in the literature. A comparison of forecasting accuracy is carried out using regional time series for models based on the conventional assumption of hom...

Focus is on efficient estimation of a dynamic space–time panel data model that incorporates spatial dependence, temporal dependence, as well as space–time covariance and can be implemented where there are a large number of spatial units and time periods. Quasi-maximum likelihood (QML) estimation in cases involving large samples poses computational...

We discuss Monte Carlo methodology that can be used to explore alternative approaches to estimating spatial regression models. Our focus is on models that include spatial lags of the dependent variable, e.g., the SAR specification. A major point is that practitioners rely on scalar summary measures of direct and indirect effects estimates to interp...

The focus is on cross-sectional dependence in panel trade ow models. We propose alternative speci cations for modeling time invariant factors such as socio-cultural indicator variables, e.g., common language and currency. These are typically treated as a source of heterogeneity elim- inated using xed effects transformations, but we nd evidence of c...

There is a great deal of literature regarding use of non-geographically based connectivity matrices or combinations of geographic and non-geographic structures in spatial econometrics models. We explore alternative approaches for constructing convex combinations of different types of dependence between observations. Pace and LeSage (2002) as well a...

Past literature has used conventional spatial autoregressive panel data models to relate patent production output to knowledge production inputs. However, research conducted on regional innovation systems points to regional disparities in both regions’ ability to turn their knowledge inputs into innovation and to access external knowledge. Applying...

Applications of spatial probit regression models that have appeared in the literature have incorrectly interpreted estimates from these models. Spatially dependent choices frequently arise in various modeling scenarios, including situations involving analysis of regional voting behavior, decisions by states or cities to change tax rates relative to...

We extend the heterogeneous coefficients spatial autoregressive panel model (HSAR) from Aquaro, Bailey, and Pesaran (2015) to the case of a heterogeneous coefficients matrix exponential spatial specification (HMESS). The HSAR is capable of producing parameter estimates for each region in the sample, that follow a spatial autoregressive process. Spa...

We extend the heterogeneous coefficients spatial autoregressive panel model from to allow for Bayesian prior information. A Markov Chain Monte Carlo estimation methodology is set forth for the Bayesian model. Monte Carlo performance results mirror those from quasi maximum likelihood estimation set forth in Matrix expressions for marginal effects us...

Spatial interaction models of the gravity type are widely used to describe origin-destination flows. They draw attention to three types of variables to explain variation in spatial interactions across geographic space: variables that characterize the origin region of interaction, variables that characterize the destination region of interaction, an...

en We investigate how R&D networks impact regional innovation, considering alternative connectivity structures based on co‐publications, co‐inventions and projects supported by the EU‐FP. Patent activity impacts on ICT during 2003–2009 for 213 European regions are quantified using a spatial Durbin model. Findings indicate that local knowledge flows...

We are interested in modeling the impact of spatial and interindustry dependence on firm-level innovation of Chinese firms The existence of network ties between cities imply that changes taking place in one city could influence innovation by firms in nearby cities (local spatial spillovers), or set in motion a series of spatial diffusion and feedba...

We show how to quickly estimate spatial probit models for large data sets using maximum likelihood. Like Beron and Vijverberg (2004), we use the GHK (Geweke-Hajivassiliou-Keane) algorithm to perform maximum simulated likelihood estimation. However, using the GHK for large sample sizes has been viewed as extremely difficult (Wang, Iglesias, & Wooldr...

We apply a heterogenous coefficient spatial autoregressive panel model to explore competition/cooperation by duopoly pairs of German fueling stations in setting prices for diesel and e5 fuel. We rely on a Markov Chain Monte Carlo (MCMC) estimation methodology applied with non-informative priors, which produces estimates equivalent to those from (qu...

Spatial interaction models represent a class of models that are used for modeling origin-destination flow data. The interest in such models is motivated by the need to understand and explain the flows of tangible entities such as persons or commodities or intangible ones such as capital, information or knowledge between regions. These models attemp...

There are several econometric advantages to the Poisson pseudo-maximum likelihood (PPML) approach to estimating relationships involving flows (Santos Silva and Tenreyro 2010). One is that the coefficients on logged explanatory variables (X) in the (exponential) relationship involving non-logged flow magnitudes as the dependent variable (y) can be i...

We introduce a Bayesian hierarchical regression model that extends the traditional least-squares regression model used to estimate gravity or spatial interaction relations involving origin-destination flows. Spatial interaction models attempt to explain variation in flows from n origin regions to n destination regions resulting in a sample of N = n...

We consider interpretation of estimates from the heterogenous coefficient spatial autoregressive panel model of Aquaro et al. (2015) and derive partial derivatives (marginal effects) for this model, an issue not discussed in Aquaro et al. (2015). We show how these differ from a conventional spatial autoregressive panel model.

We apply a heterogenous coefficient spatial autoregressive panel model to explore competition/cooperation by duopoly pairs of German fueling stations in setting prices for diesel and E5 fuel. We rely on a Markov Chain Monte Carlo (MCMC) estimation methodology applied with non-informative priors, which produces estimates equivalent to those from (qu...

A wide variety of spatial regression specifications that include alternative types of spatial dependence (e.g., lagged values of the dependent variable, spatial lags of explanatory variables, dependence in the model disturbances) have been the focus of a literature on statistical tests for distinguishing between alternative specifications. LeSage (...

Anderson and van Wincoop (American Economic Review (2003), 69:106) make a convincing argument that traditional gravity equation estimates are biased by the omission of multilateral resistance terms. They show that these multilateral resistance terms are implicitly defined by a system of non-linear equations involving all regions' GDP shares and a g...

Forecasting performance of spatial versus non-spatial Bayesian priors applied to a large vector autoregressive model that includes the 48 lower US states plus and the District of Columbia is explored. Accuracy of one- to six-quarter-ahead personal income forecasts is compared for a model based on the Minnesota prior used in macroeconomic forecastin...

There is near universal agreement that estimates and inferences from spatial regression models are sensitive to particular specifications used for the spatial weight structure in these models. We find little theoretical basis for this commonly held belief, if estimates and inferences are based on the true partial derivatives for a well-specified sp...

In this study, we consider R&D collaboration networks as a mechanism that modifies knowledge flows in space, and hence as another source of interaction among regional innovation processes. Our objective is to understand the relative role of spatial neighbors and network neighbors on patenting performance of regions. We make use of data on R&D colla...

Taking a Bayesian perspective on model uncertainty for static panel data models proposed in the spatial econometrics literature considerably simplifies the task of selecting an appropriate model. A wide variety of alternative specifications that include various combinations of spatial dependence in lagged values of the dependent variable, spatial l...

We examine the provincial-level relationship between domestic Chinese intellectual property (IP) and knowledge stocks using a space–time panel model and data set covering monthly patent activity over the period 2002–2010. The goal of the modeling exercise is to explore the elasticity response of IP to knowledge stocks classified by type of creator...

Past applications of spatial regression models have frequently interpreted the parameter estimates of models that include spatial lags of the dependent variable incorrectly. A discussion of issues surrounding proper interpretation of the estimates from a variety of spatial regression models is undertaken. We rely on scalar summary measures proposed...

Spatial interaction or gravity models have been used in regional science to model flows that take many forms, for example, population migration, commodity flows, traffic flows, and knowledge flows, all of which reflect movements between origin and destination regions. This chapter focuses on spatial autoregressive extensions to the conventional lea...

Standard regression models described by Anselin (1988) rely on spatial dependence and spatial weight structures where the sample involves n regions. Lesage and Pace (2008) extend these models to a family of spatial origin-destination (OD) models involving N=n2 OD pairs. In this study we model internal migration of Turkey via spatial econometric mod...

This study suggests a two-step approach to identifying and interpreting regional convergence clubs in Europe. The first step involves identifying the number and composition of clubs using a space-time panel data model for annual income growth rates in conjunction with Bayesian model comparison methods. A second step uses a Bayesian space-time panel...

Spatial interaction or gravity models have been used to model flows that take many forms, for example population migration, commodity flows, traffic flows, all of which reflect movements between origin and destination regions. We focus on how to interpret estimates from spatial autoregressive extensions to the conventional regression-based gravity...

Regional scientists frequently work with regression relationships involving sample data that is spatial in nature. For example, hedonic house-price regressions relate selling prices of houses located at points in space to characteristics of the homes as well as neighborhood characteristics. Migration, commodity, and transportation flow models relat...

Regional scientists frequently work with regression relationships involving sample data that is spatial in nature. For example, hedonic house-price regressions relate selling prices of houses located at points in space to characteristics of the homes as well as neighborhood characteristics. Migration, commodity, and transportation flow models relat...

The focus here is on the log-normal version of the spatial interaction model. In this context, we consider spatial econometric specifications that can be used to accommodate two types of dependence scenarios, one involving endogenous interaction and the other exogenous interaction. These model specifications replace the conventional assumption of i...

We show that use of ordinary least-squares to explore relationships involving firm-level stock returns as the dependent variable in the face of structured dependence between individual firms leads to an endogeneity problem. This in turn leads to biased and inconsistent least-squares estimates. A maximum likelihood estimation procedure that will pro...

Spatial filtering in various forms has become a popular way to address spatial dependence in statistical models (Griffith, 2003; Tiefelsdorf & Griffith, 2007). However, spatial filtering faces computational challenges for large n as the current method requires order of n3 operations. This manuscript demonstrates how using iterative eigenvalue routi...

Applications of spatial probit regression models that have appeared in the literature have incorrectly interpreted estimates from these models. Spatially dependent choices frequently arise in various modeling scenarios, including situations involving analysis of regional voting behavior, decisions by states or cities to change tax rates relative to...

Gravity or spatial interaction models have a long history in regional science and international trade. In the empirical trade literature, Poisson pseudo-maximum likelihood estimation methods (PPML) have become popular as a way of dealing with several econometric issues that arise when modeling origin-destination flows [e.g., Silva and Tenreyro (200...

We introduce a Bayesian hierarchical regression model that extends the traditional least-squares regression model used to estimate gravity or spatial interaction relations involving origin-destination flows. Spatial interaction models attempt to explain variation in flows from n origin regions to n destination regions resulting in a sample of N = n...

LeSage and Pace (2009) consider the impact of omitted variables in the face of spatial dependence in the disturbance process of a linear regression relationship. Remarkably, they show that this can lead to a spatial regression model specification containing a spatial lag of the dependent and explanatory variables, providing an econometric as oppose...

We explore origin-destination forecasting of commodity flows between 15 Spanish regions, using data covering the period from 1995 to 2004. The one-year-ahead forecasts are based on a recently introduced spatial autoregressive variant of the traditional gravity model. Gravity (or spatial interaction models) attempt to explain variation in N=n2 flows...

We analyzed the business reopening process in New Orleans after Hurricane Katrina, which hit the region on August 29, 2005, to better understand what the major predictors were and how their impacts changed through time. A telephone survey of businesses in New Orleans was conducted in October 2007, 26 months after Hurricane Katrina. The data were an...

(DOCX)

Questions surrounding the impact of population migration on social capital is the focus of this study. Putnam observed that “for people as for plants, frequent repotting disrupts root systems. It takes time for a mobile individual to put down new roots.” However, because of a trending decrease in mobility over time, Putnam rules out migration as an...

The authors develop an empirical approach to examine static and dynamic knowledge externalities in the context of a regional total factor productivity (TFP) relationship. Static externalities refer to current period scale or industry-size effects that have been labeled localization externalities or region-size effects known as agglomeration externa...

Most spatial econometrics work focuses on spatial dependence in the regressand or disturbances. However, Lesage and Pace (2009) as well as Pace and LeSage2009 showed that the bias in β from applying OLS to a regressand generated from a spatial autoregressive process was exacerbated by spatial dependence in the regressor. Also, the marginal likeliho...

If you are trying to reopen a business after a disaster like Hurricane Katrina, how is your decision affected by whether or not your neighbours are reopening as well?James LeSage, R. Kelley Pace, Richard Campanella, Nina Lam and Xingjian Liu take cycle rides through a recovering New Orleans.

We use a space-time dynamic panel model to quantify the impact of Hurricane Ike on Texas county-level employment for the immediately affected disaster counties plus neighboring counties. While the hurricane event created a loss of over 314,000 employment in the 44 county disaster area, employment in some counties gained over 24,000 jobs as a result...

We analyse decisions to reopen in the aftermath of Hurricane Katrina made by business establishments on major business thoroughfares in New Orleans by using a spatial probit methodology. Our approach allows for interdependence between decisions to reopen by one establishment and those of its neighbours. There is a large literature on the role that...

This study provides evidence concerning the impact of anticipated and unanticipated components of the weekly money supply announcements on stock market returns in the United States and Canada on the date after the announcement. The innovative aspect of this study is the use of a multiprocess mixture model recently proposed by Gordon and Smith (1990...

We show how to quickly estimate spatial probit models for large data sets using maximum likelihood. Like Beron and Vijverberg (2004), we use the GHK (Geweke-Hajivassiliou-Keene) algorithm to perform maximum simulated likelihood estimation. However, using the GHK for large sample sizes has been viewed as extremely difficult (Wang, Iglesias, and Wool...

These articles provide a discussion of studies presented in a session on spatial econometrics, focusing on the ability of spatial regression models to quantify the magnitude of spatial spillover impacts. Both articles presented argue that a proper modeling of spatial spillovers is required to truly understand the phenomena under study, in one case...

ABSTRACT This paper seeks to develop our understanding of the somewhat diffuse nature of technological externalities and space by associating a geographical dimension with the sectoral dimension. Using a panel data set containing French patents as well as private and public research expenditures by industry and region over the period from 1992 to 2...

ABSTRACT We provide a Bayesian spatial Markov Chain Monte Carlo model composition (MC3) analysis of growth rates in European regional patenting activity. Based on theoretical models on innovation and growth, we identify a large set of candidate explanatory variables that characterize regional stocks of knowledge, including: human resources devoted...

County-level estimates of employment, unemployment, and the unemployment rate are not produced directly from a sample survey; rather, they are developed through models that use information on the labor force from a number of statistical programs such as the CPS (Current Population Survey), CES (Current Employment Statistics), and State Unemployment...

Most spatial econometrics work focuses on spatial dependence in the regressand or disturbances. However, LeSage and Pace (2009) show that the bias from applying OLS to a regressand generated from a spatial autoregressive process was exacerbated by spatial dependence in the regressor. Also, the marginal likelihood function or restricted maximum like...

Although salary benchmarking is widely used to help set compensation, there has been a lack of attention to the statistical implications of this practice on compensation patterns of peer institutions. We adapt some empirical tools from spatial econometrics to analyze compensation decisions exhibiting peer-group dependence, and apply the methods to...

Spatial regression methodology has been around for most of the 50 years (1961-2011) that the Southern Regional Science Association has been in existence. Cliff and Ord (1969) devised a parsimonious specification for the structure of spatial dependence among observations that could be used to empirically model spatial interdependence. Later work (Cl...

It is frequently assumed that regional observations on local government behavior, voters, regional taxes, etc. can be analyzed using ordinary least-squares (OLS) methods. We discuss spatial regression models in empirical studies of public choice issues using impacts arising from population migration on the provision of county-level government servi...

There is near universal agreement that estimates and inferences from spatial regression models are sensitive to particular specifications used for the spatial weight structure in these models. We find little theoretical basis for this commonly held belief, if estimates and inferences are based on the true partial derivatives for a well-specified sp...

Spatial interaction models of the gravity type are used in conjunction with sample data on flows between origin and destination locations to analyse international and interregional trade, commodity, migration and commuting patterns. The focus is on the classical log-normal model version and spatial econometric extensions that have recently appeared...

Spatial regression models allow us to account for dependence among observations, which often arises when observations are collected from points or regions located in space. The spatial sample of observations being analyzed could come from a number of sources. Examples of point-level observations would be individual homes, firms, or schools. Regiona...

Estimates and inferences that arise from use of empirical models include uncertainty arising from a number of sources. Coefficient estimates produced using statistical regression methods embody uncertainty that we attribute to noise that arises in the process that generated our sample data. There are other sources of uncertainty related to issues o...

A Gibbs sampling (Markov chain Monte Carlo) method for estimating spatial autoregressive limited dependent variable models is presented. The method can accommodate data sets containing spatial outliers and general forms of non-constant variance. It is argued that there are several advantages to the method proposed here relative to that proposed and...

This paper explores the contribution of knowledge capital to total factor productivity differences among regions within a regression framework. We provide an econometric derivation of the relationship and show that the presence of latent/unobservable regional knowledge capital leads to a model relationship that includes both spatial and technologic...