The NCSTAR model as an alternative to the GWR model

Marie Lebreton

Physica A: Statistical Mechanics and its Applications, 2005, vol. 355, issue 1, 77-84

Abstract: This paper compares the GWR model, usually used to integrate and examine the spatial heterogeneity of a relationship, and the NCSTAR model. The former will give a vector of local parameter estimates for each observation of the data set, according to its nearest neighbors in space. However, it supposes that all variables enter linearly the model. To correct this failure, a NCSTAR model is proposed. It can be seen as a linear model which coefficients are given by the outputs of an ANN model. These outputs can be related not only to geographical variables but also to social, financial or economic variables (according the nature of the relationship under study) via a nonlinear function which functional form has not to be specified. Moreover, the confidence intervals for the NCSTAR estimates can be computed.

Keywords: Neural network models; Spatial heterogeneity; Statistical inference (search for similar items in EconPapers)
Date: 2005
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378437105002785
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:355:y:2005:i:1:p:77-84

DOI: 10.1016/j.physa.2005.02.069

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().