Gordon F. Mulligan

Agglomeration and Central Place Theory: A Review of the Literature

This paper reviews and evaluates the analytical literature on the interdependencies of agglomeration and central place theory. It is emphasized that economic agents (firms, households) tend to cluster at points of differential centrality on the economic landscape, and that this clustering process can provide even further savings to both producers and consumers. The agglomeration phenomenon is examined at three scales: (1) firm-level analysis focuses on uncertainty, shopping behavior, and spatial equilibria of the economy; (2) settlement-level analysis focuses on static and dynamic city-size models; and (3) system-level analysis focuses on city-size distributions, flows, and evolutionary processes in central place systems. The paper ends with suggestions concerning future research directions.

Using Geographically Weighted Regression to Explore Local Crime Patterns

The present research examines a structural model of violent crime in Portland, Oregon, exploring spatial patterns of both crime and its covariates. Using standard structural measures drawn from an opportunity framework, the study provides results from a global ordinary least squares model, assumed to fit for all locations within the study area. Geographically weighted regression (GWR) is then introduced as an alternative to such traditional approaches to modeling crime. The GWR procedure estimates a local model, producing a set of mappable parameter estimates and t-values of significance that vary over space. Several structural measures are found to have relationships with crime that vary significantly with location. Results indicate that a mixed model— with both spatially varying and fixed parameters—may provide the most accurate model of crime. The present study demonstrates the utility of GWR for exploring local processes that drive crime levels and examining misspecification of a global model of urban violence.

Spatial Flows and Competing Central Places: Towards a General Theory of Hierarchical Interaction

This paper presents a variation of Fotheringhams competing destinations model using categorized information on spatial flows in a central place system. A competing central place model is developed using spatially defined choice sets for origin — destination pairs by threshold distance and central place order. The competing central place generalization is empirically tested by undertaking a comparative analysis of 1980 domestic airline passenger traffic amongst selected cities in the continental United States. A host of modeling strategies are contrasted and the effects of mass, separation, and competitive forces noted in the presence or absence of hierarchical data. The production-constrained competing central place specification is shown to exhibit not only greater explanatory power than Fotheringhams competing destinations model, but also significant reductions in potential multicollinear relations between regressors. The model is later extended to incorporate an intervening opportunities filter. Competitive flow patterns between paired origins and destinations are then delimited by geographic range, compatibility, and the impeding effects of substitute and/or intervening flows within a hierarchical network.

The Determinants of Crime in Tucson, Arizona1

This paper examines the geography of violent crime across the neighborhoods of Tucson and South Tucson, Arizona. The research is informed by the tenets of modern social disorganization theory, which has a strong ecological or environmental basis. Three different crime indices are computed; each represents an annual average during the five-year period 1995-1999. The most comprehensive index captures aggravated assaults, homicides, robberies, and sexual assaults. After providing a factor-ecological study of the study area, using 27 variables taken from the 1990 census, various regression models are developed to explain violent crime patterns. These models use a smaller array of ten demographic, economic, and social attributes to predict patterns at the block group level. A number of variables are found to be significant across all models, thereby providing further support for social disorganization theory. Stability in the signs and values of the estimates suggest that a general model of violent crime can be established for the study region. The paper closes with a short discussion of some public policy implications.

MEASURING SPATIAL FOCUSING IN A MIGRATION SYSTEM

Equality indexes used in other geographical contexts may be used to gauge the degree of spatial focusing in an entire migration system or within the gross in- and out-migration fields of specific regions. They provide useful indicators of overall shifts in the patterns of interregional migration and can help give insight into the population redistributive roles played by specific regions. Perhaps the most common equality index used to measure income distribution is the Gini coefficient, yet it appears almost never to have been applied in migration research. In this paper we set forth a variety of Gini indexes to be used for different migration analyses and illustrate their application with recent data on U.S. interstate movements. We argue that the Gini index provides some singularly useful insights that differ from those afforded by other measures more commonly found to date in the migration analyst’ s toolkit.

Initial Diagnostics of a Regional Adjustment Model

Adjustment models are used increasingly to analyze population and employment changes in regional economies. However, questions remain about the most appropriate geographic scales and time lags for these models. In this paper we estimate a well-known adjustment model for a recent 25-year period in the USA. Regional population and employment changes (levels and densities) are examined at three scales (states, Bureau of Economic Analysis regions, counties) using various time lags (one to ten years). Two-stage least squares regression estimates, based on Regional Economic Information System data running between 1969 and 1994, are generated and discussed. Analysis is restricted to the core relationships between population and employment; the roles of other exogenous variables, normally included in adjustment models, are not considered. Instead, concern is focused on issues such as stability and directional causality of the interacting population—employment systems. Some brief suggestions regarding future research conclude the paper.

Hedonic Estimates of Lodging Rates in the Four Corners Region

In many industries, insufficient attention has been given to how location affects prices. One such industry is lodging. This article examines room rates for budget hotels and motels in four southwestern U.S. states during 1998. Using hedonic analysis, published prices are estimated for nearly 600 establishments belonging to six national chains. OLS regression uncovers how site attributes (pools, spas, and complimentary breakfasts) and situation attributes (temperature, interstate location, and specialization of the local economy) affect room rates. Prices for overnight stays during summer and winter seasons are examined. Differential effects of site and situation attributes on price heterogeneity are discussed.

Functional Form and Spatial Interaction Models

This paper is an examination of functional form and functional misspecification in regression-based spatial interaction models. Box–Cox transformations are used to model US state-to-state labor migration. Attention is given to the production-constrained gravity model, the competing and intervening destinations (CID) model, and an extension of the CID model which uses dummy variables and an iterative transformation procedure. Statistical evidence supports the argument that the use of highly restrictive log-linear specifications may be inappropriate and problematic. Implications for spatial interaction modeling using general nonrestrictive functional forms are discussed.

EQUALITY MEASURES AND FACILITY LOCATION

A review of the literature indicates that fairly simplistic measures of equality in travel distances are normally used in facility location studies. Two popular criteria, those of minimizing the maximal distance and the range, are known to be sensitive to the extreme values (locations of users) of the problem. This paper recommends that distributional equality should be used instead in most locational studies. Using a simple spatial setting, the paper offers a comparative analysis of equality curves based on the following measures: Gini coefficient, mean deviation, Hoovers concentration index, variance (standard deviation), and Theils entropy index.

REGRESSION ESTIMATES OF ECONOMIC BASE MULTIPLIERS FOR SMALL COMMUNITIES

Applied researchers are increasingly realizing that small-area impact models should be calibrated by survey-based data. This paper uses a comprehensive, cross-sectional data set to calibrate the ec...