Location choices of newly created establishments: Spatial patterns at the aggregate level

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractThis paper explores the problems associated with the location choice of newly created establishments at the aggregate level. Much work has been done in this domain, however, several issues arise when analyzing involved phenomena, which scholars have yet to fully explore: 1) addressing the excess of zeros problem in the location choice model in highly heterogeneous geographic areas and 2) determining an appropriate way to accommodate spatial effects for location decisions. We tested models that include both stocks of preexisting establishments and variables that represent measures of accessibility to the workforce and population, proximity to shops, services, transport infrastructure, availability of land, as well as prices and tax levels.We concluded that an establishment does not act in isolation during its decision-making processes and that it is likely to be influenced by other establishments located nearby. When selecting the appropriate location in which to set up in the market, an establishment may consider not only the characteristics of a particular area, but also the characteristics of neighboring zones. Having estimated 84 nested and non-nested count data models, we found that the hurdle models are preferred for taking into account the presence of excess zeros. Hurdle models offer greater flexibility in modeling zero outcomes and relax the assumption that the zero observations and the positive observations come from the same data generating process. In addition, the paper finds that the models tested with the distance matrix indicate that the incorporation of spatial spillovers leads to an enhancement in the models' performance.

A comparison of Euclidean Distance, Travel Times, and Network Distances in Location Choice Mixture Models

“…They described the establishment/firm location determinants, the econometric methods used in these investigations, and their main findings 6 . However, only recently has the importance of spatial effects in this context has been emphasized (Bhat et al, 2014, Buczkowska and Lapparent, 2014, Liviano-Solís and Arauzo-Carod, 2013, Liesenfeld et al, 2013, Lambert et al, 2010, Klier and McMillen, 2008. As shown by Nguyen et al (2012), an establishment does not act in isolation during its decisionmaking processes and is likely to be influenced by other establishments located nearby.…”

“…The methodology is applied to the location choice of newly created establishments in the Paris region. Recent works have emphasized the importance of spatial effects in this context (Bhat et al, 2014, Buczkowska and Lapparent, 2014, Liviano-Solís and Arauzo-Carod, 2013, Liesenfeld et al, 2013, Lambert et al, 2010, Klier and McMillen, 2008). Yet, whenever the distance measure was used in the weight matrix to implement the spatial effects or spatial spillovers in location choice models, no discussion was provided on the choice of the distance measure itself and the Euclidean distance was utilized.…”

“…On the basis of former work by Buczkowska and Lapparent (2014), we extend their model by estimating a mixture of hurdle-Poisson models whereby two latent classes are used. Each class uses a different definition of distance to capture spatial spillovers.…”

Extending a Smooth Parameter Model to Firm Location Analyses: The Case of Natural Gas Establishments in the United States

“…Arauzo‐Carod and Manjón‐Antolín () used Local Indices of Spatial Association (Anselin, ) to determine optimal lags for location determinants, which were subsequently used as covariates in their count model. In a similar approach, Buczkowska and de Lapparent () used nonlinear cross‐regressions to incorporate directly spillover effects into the conditional mean function.…”

“…In the same cross‐section, firms may collocate in regions endowed with key raw materials or seek a limited number of feasible sites in highly agglomerated regions. A standard econometric solution to this mode of censoring is to model firm location activity with zero‐inflated count regressions, such as the zero‐inflated Poisson (ZIP), zero‐inflated negative binomial, or hurdle models (List, ; Gabe, ; Arauzo‐Carod, ; Manjόn‐Antolín and Arauzo‐Carod, ; Liviano and Arauzo‐Carod, , ; Buczkowska and de Lapparent, ). The hurdle/zero‐inflated class of count regressions control for nonlinear spatial components related to the observed geographic distribution of resource patterns explaining firm location events that would otherwise be omitted from standard Poisson or negative binomial regressions.…”