Spatial Econometrics – Definition, Concepts, Types of Econometric Models, Durbin Model, Applications, Advantages, Disadvantages, Differences With Standard Econometrics, Spatial Correlation

Home / Glossary index / Spatial Econometrics – Definition, Concepts, Types of Econometric Models, Durbin Model, Applications, Advantages, Disadvantages, Differences With Standard Econometrics, Spatial Correlation

What is Spatial Econometrics ?

Spatial econometrics is a branch of economics that deals with the study of economic phenomena that exhibit spatial dependence . In other words, it deals with the study of how economic activity is related to the physical space in which it takes place . This branch of economics has its roots in classical economics, which focused on the study of how economic activity was related to the location of factors of production . Classical economists developed theories of how businesses locate themselves in relation to their markets and to each other . These theories formed the basis for the development of modern spatial economics .

Contemporary spatial economics covers a wide range of topics, from the analysis of housing markets to the study of Transport infrastructure . It encompasses both microeconomic and macroeconomic analysis and makes use of a variety of tools and techniques, including mathematical modeling, statistical analysis and Geographic Information Systems (GIS) .

The aim of spatial econometrics is to identify, quantify and explain relationships between economic variables that are spatially dependent . These relationships can be direct or indirect and can be positive or negative in nature . Spatial econometric models can be used to test hypotheses about how economic activity is affected by location-specific factors such as accessibility, agglomeration economies or local amenities . They can also be used to examine relationships between different regions or countries or to study how changes in one region (such as a new transport link) might impact economic activity in another region .

Overall, spatial econometrics is a powerful tool for understanding how economic activity is shaped by location . It can provide insight into the fundamental factors that drive economic development and growth and help to inform public policy decisions that impact geographically distributed populations .

What Are The Basic Principles and Concepts of Spatial Econometrics ?

Spatial econometrics is a rapidly growing field of economics that studies the relationships between economic variables that are geographically determined . The main aim of spatial econometrics is to develop methods and models that can be used to better understand how economic activity is spatially dependent and how this affects policy making .

There are a number of basic principles and concepts that are important for understanding spatial econometrics . First, it is important to understand the concept of spatial autocorrelation . This occurs when the values of a variable are more similar to the values of nearby observations than they are to observations that are further away . Spatial autocorrelation can have a number of causes, including proximity to market access, natural resources or other factors .

Second, it is also important to understand the concept of spillovers . This occurs when the activities of one firm or individual have an impact on the activity of another firm or individual in the same location . Spillovers can be positive or negative; for example, positive spillovers may occur when one firm opens a new factory and creates jobs in the community, while negative spillovers may occur when a firm pollutes the air or water in a community .

Third, another important concept in spatial econometrics is that of agglomeration economies . This refers to the fact that firms in close proximity to each other often enjoy lower costs due to shared infrastructure and knowledge spillovers . Agglomeration economies can have positive effects on economic growth, as firms in close proximity can benefit from shared resources and expertise .

Finally, spatial econometrics also examines the effect of distance on economic activity . This is known as the law of distance decay, which states that the change in economic activity between two points increases as their distance increases . Distance has an important impact on many aspects of economics, from labor markets to trade patterns and understanding this relationship can help improve policy decisions .

What Are The Types of Econometric Models Used in Spatial Analysis ?

There are many types of econometric models that can be used in spatial analysis . Some of the most common include structural equation models, autoregressive models and panel data models . Each type of model has its own strengths and weaknesses, so it is important to choose the right model for the specific dataset and research question at hand .

Structural equation models (SEMs) are commonly used in spatial analysis because they allow for the estimation of direct and indirect effects between variables . SEMs are particularly well-suited for studying causality . However, SEMs can be computationally intensive, so they may not be practical for very large datasets .

Autoregressive models are another type of econometric model that is often used in spatial analysis . These models focus on the relationship between a dependent variable and a set of lagged independent variables . Autoregressive models are typically easier to estimate than SEMs, but they may not be as accurate in predicting causal relationships .

Panel data models are a third type of econometric model that can be used in spatial analysis . These models focus on estimating relationships between variables over time . Panel data models are often used when researchers have access to repeated measures for the same units (e .g ., individuals or firms) . Panel data models can be quite complex, so they may not be appropriate for all datasets and research questions .

What is The Spatial Econometrics Durbin Model ?

The Spatial Durbin model is a type of spatial econometric model that is used to analyze the relationship between a dependent variable and independent variables when there is a spatial correlation between the observations . This model is used extensively in various fields such as Economics, Sociology and Geography .

The Spatial Durbin model is typically estimated using OLS regression with a correction for the spatial autocorrelation . The correction term is usually added to the error term of the regression equation and is often referred to as the "spatial error" term . The presence of spatially correlated errors can lead to biased and inconsistent estimates if not accounted for properly .

There are two main types of Spatial Durbin models : the first-order and second-order models . The first-order model includes only one lag of the dependent variable while the second-order model includes two lags . Higher order models can be used but are less common due to the computational burden involved .

The coefficients in a Spatial Durbin model are typically interpreted in a similar way as other regression coefficients . For example, a positive coefficient on an independent variable would indicate that an increase in that variable is associated with an increase in the dependent variable (holding all other variables constant) .

What Are The Examples of Applications Using Spatial Econometrics ?

There are many applications for spatial econometrics . Here are a few examples :

  • Evaluating the impact of a new road or railway on property values
  • Estimating the effect of environmental regulations on firm location decisions
  • Analyzing the determinants of crime rates across neighborhoods
  • Studying the relationship between house prices and income levels in different regions
  • Investigating the spread of infectious diseases through a population
  • Modeling the relationship between land values and location-specific services
  • Analyzing the relationship between proximity to facilities and job opportunities .

What Are The 10 Main Advantages of Using Spatial Econometrics ?

Here are the 10 main advantages of using spatial Econometrics :

  • Spatial econometrics methods allow for the inclusion of space as a key determinant in economic models .
  • Spatial econometrics techniques can help to identify and quantify the relationships between different economic units, such as regions or countries .
  • Spatial data can be used to improve our understanding of how economic activities are distributed across geographical areas .
  • The methods can provide insight into how changes in one location can affect other nearby areas .
  • Spatial econometrics can be used to study the impact of transport infrastructure on regional economies .
  • The methods can also be employed to assess the competitiveness of different locations within a country or region .
  • Additionally, spatial econometrics techniques can help us understand agglomeration effects and other economic phenomena that display scale economies .
  • By incorporating space into our models, we can account for endogeneity issues that may bias our results if left unaddressed .
  • Using spatial data and methods can add an important policy dimension to our research by providing policy-relevant insights at the local level .
  • Finally, the use of spatial econometrics can significantly reduce computation time and simplify the analysis process .

What Are The 10 Main Disadvantages of Using Spatial Econometrics ?

There are a number of disadvantages to using spatial econometrics that should be considered before undertaking any analysis . These include :

  • Spatial econometrics is a relatively new field and therefore there is limited experience and understanding of the methods and techniques .
  • The methods and techniques used in spatial econometrics are often complex and require a high level of statistical expertise .
  • Spatial data can be difficult to obtain, particularly if specific data sets are required for the analysis .
  • The quality of spatial data can vary significantly, which can impact on the results of the analysis .
  • There may be problems with collinearity in the data, which can limit the interpretation of the results .
  • The results of spatial econometric analyses can be sensitive to small changes in the data, making them difficult to replicate .
  • There can be problems with endogeneity in spatial econometric models, which can lead to biased estimates .
  • Some types of spatial data are better suited to certain types of analyses than others, so it is important to choose the right type of data for the question being asked .
  • It is often necessary to make assumptions about the underlying relationships in order to conduct a spatial econometric analysis, which can lead to errors if these assumptions are not valid .
  • Conducting a spatial econometric analysis often requires considerable time and effort, which may not be feasible for all research projects .

Finally, the results of a spatial econometric analysis can sometimes be difficult to interpret and communicate to different audiences .

What Are The 10 Main Differences Between Spatial Econometrics And Standard Econometrics ?

Here are the 10 main differences between spatial Econometrics and standard Econometrics :

  • Spatial econometrics incorporates spatial relationships into the analysis, while standard econometrics does not .
  • Spatial econometrics models allow for spillover effects between units, while standard econometrics models do not .
  • Spatial autocorrelation is taken into account in spatial econometric models, while it is not in standard econometric models .
  • In spatial econometrics, both cross-sectional and time-series data can be used, while in standard econometrics, only cross-sectional data can be used .
  • In spatial econometrics, both observational and experimental data can be used, while in standard econometrics, only observational data can be used .
  • Spatial lag and error models are specific to spatial econometrics, while they are not part of standard econometrics .
  • Geographically weighted regression is a technique unique to spatial econometrics, while it is not part of standard econometrics .
  • The Durbin-Watson test statistic is modified in some forms of spatial econometrics to account for autocorrelation, while in standard econometrics it is not modified .
  • Hausman tests are common in spatial but not in Standard Econometrics
  • Finally Bayesian methods are used more frequently in spatial econometrics than standard econometrics .

What is Spatial Correlation in Econometrics ?

In econometrics, spatial correlation is a type of dependence between variables that occurs when those variables are geographically close to each other . This correlation can be positive (meaning the two variables move in the same direction) or negative (meaning the two variables move in opposite directions) . Spatial correlation is important to consider when analyzing data that has a geographic component, because it can impact the results of statistical tests and models .

There are several methods for measuring spatial correlation, including the Moran’s I statistic and the Geary’s C statistic . In addition, various software packages offer tools for visualizing and analyzing spatial data . When working with spatial data, it is important to be aware of the potential for bias due to spatial autocorrelation .

Finally, it is important to note that spatial correlation is not the same as temporal correlation . Temporal correlation exists when two variables have a relationship over time, whereas spatial correlation relates to geographic proximity .


Spatial econometrics is an increasingly complex and important area for researchers in the field of economics . By understanding the basics, you are well on your way to performing sophisticated analyses that can provide valuable insights and policy recommendations .

With a stronger grasp on spatial econometrics, you will be able to make sure that your data analysis provides more reliable results with better interpretation when combined with other economic theories .

Hello everyone ! I am the creator and webmaster of website . Specialized in Technology Intelligence and Innovation ( Master 1 Diploma in Information and Systems Science from the University of Aix-Marseille, France ), I write tutorials allowing you to discover or take control of the tools of ICT or Technological Intelligence . The purpose of these articles is therefore to help you better search, analyze ( verify ), sort and store public and legal information . Indeed, we cannot make good decisions without having good information !

scroll to top