Premium
PERSPECTIVES ON SPATIAL ECONOMETRICS: LINEAR SMOOTHING WITH STRUCTURED MODELS
Author(s) -
McMillen Daniel P.
Publication year - 2012
Publication title -
journal of regional science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.171
H-Index - 79
eISSN - 1467-9787
pISSN - 0022-4146
DOI - 10.1111/j.1467-9787.2011.00746.x
Subject(s) - smoothing , spatial econometrics , nonparametric statistics , econometrics , contiguity , parametric statistics , semiparametric regression , spatial dependence , parametric model , nonparametric regression , semiparametric model , spatial analysis , mathematics , statistics , computer science , operating system
Though standard spatial econometric models may be useful for specification testing, they rely heavily on a parametric structure that is highly sensitive to model misspecification. The commonly used spatial AR model is a form of spatial smoothing with a structure that closely resembles a semiparametric model. Nonparametric and semiparametric models are generally a preferable approach for more descriptive spatial analysis. Estimated population density functions illustrate the differences between the spatial AR model and nonparametric approaches to data smoothing. A series of Monte Carlo experiments demonstrates that nonparametric predicted values and marginal effect estimates are much more accurate then spatial AR models when the contiguity matrix is misspecified.