Method and Application of Spatial Probit Model to the Business Return to New Orleans after Hurricane Katrina

Liu, Xingjian
Journal Title
Journal ISSN
Volume Title
This study employs a theoretical framework from micro-scale retail location studies and implements a spatial autoregressive probit model to account for spatial dependence among firms' decisions and thus identify determinants of business return to New Orleans after Hurricane Katrina. The spatial probit approach allows for interdependence between decisions to reopen by one establishment and those of its neighbors. There is a large literature on the role played by spatial dependence in firm location decisions, and we find evidence of strong dependence in firm's decisions to reopen in the aftermath of a natural disaster such as Katrina. This interdependence has important statistical implications for how we analyze business recovery after disasters, as well as government aid programs. In order to determine the right model specification, a Monte Carlo experiment is conducted to extends information criteria for selecting alternative model specifications in spatial econometric modeling, and provides some insight about performance of different ~odel selection tools for choosing a spatial weight matrix.
Spatial analysis, Economic developments, Hurricane Katrina, Louisiana, New Orleans, Statistics
Liu, X. (2010). <i>Method and application of spatial probit model to the business return to New Orleans after Hurricane Katrina</i> (Unpublished thesis). Texas State University-San Marcos, San Marcos, Texas.