Implementing Representations of Space in Economic Geography*

Abstract

Since spatial issues have become more important in economic theory, it is of interest to examine how space is represented. In empirical terms, this concerns at least the representation of distance and proximity. Both of these may be represented and operationalized in a number of ways, with possible consequences for inferences when modeling. This question is related to the representation of spatial entities, and itself plays into the treatment of spatial dependence as substantive and/or just a nuisance. Because other disciplines face similar questions-for example ecology or epidemiology, their conceptualizations and operationalizations of space will also be used for comparative purposes.

Thirty years of spatial econometrics

“…In recent years, the interest in spatial analysis in general and spatial econometric analysis in particular has seen an almost exponential growth, especially in the social sciences (Goodchild et al. 2000; Bivand 2008). For example, Table 1.1 in Anselin et al.…”

“…As mentioned earlier, there has been a virtual explosion in the number of articles dealing with spatial data analysis and spatial econometrics appearing in both the econometrics journals as well as applied field journals in economics (for extensive examples, see Anselin et al. 2004b; Bivand 2008). This is in addition to a continued steady stream of articles in regional science and spatial analysis journals.…”

“…By this time, the lack of readily available software can no longer be invoked as an impediment to carry out spatial analysis. Some reviews of the state of the art in software tools can be found in Anselin (2000, 2005); Rey and Anselin (2006); and Bivand (2008) among others.…”

Revisiting Guerry’s data: Introducing spatial constraints in multivariate analysis

“…The spatial weighting matrix. The first step of spatial autocorrelation analysis is to define a n × n spatial weighting matrix, usually denoted W. This matrix is a mathematical representation of the geographical layout of the region under study [Bivand (2008)]. The spatial weights reflect a priori the absence (w ij = 0), presence or intensity (w ij > 0) of the spatial relationships between the locations concerned.…”

Revisiting the Boston Data Set (Harrison and Rubinfeld, 1978): A Case Study in the Challenges of System Articulation

“…Usually, it is the micro-scale variation of a scale smaller than the observation units (or the distances between them) that is omitted -however, omitted large scale trends may be seen as autocorrelation rather than misspecification. Bivand (2008) provides an extended discussion of some of the consequences of passing perhaps too rapidly through system articulation for statistical inference from spatial data.…”