Spatial Autocorrelation Or Model Misspecification?

By Daniel P. McMillen. 2003

125 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4d602bdf8354ae95d77d6c3a3c1f2eae2f5b2a34

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

On spatial econometric models, spillover effects, and W (2013, methodology): “McMillen's (2012) critique mainly focuses on the limitations of the spatial lag model (SAR) and the spatial error model (SEM), and is partly based on previous work (McMillen, 2003, 2010).”
A Simulation-Based Study of Geographically Weighted Regression as a Method for Investigating Spatially Varying Relationships (2011, methodology): “McMillen (2003), for example, illustrates how the nonparametric approach can be used to provide a better fit to the data, and to diagnose parametric model misspecification.”
The Spatial Durbin Model and the Common Factor Tests (2006, background): “Using particular but relevant modelling cases, López-Bazo & Fingleton arrive at the same conclusion reached previously by McMillen (2003): in effect, what habitually underlies models with residual autocorrelation is a problem of misspecification of the equation due, in general, to the omission of…”
Spatial Heterogeneity in Hedonic House Price Models: The Case of Austria (2014, background): “However, as McMillen (2003) points out, unexplained similarities between neighboring houses can result in SAC, which is captured using spatial autoregressive models.”
Comparing implementations of global and local indicators of spatial association (2018, background): “Both global and local measures may detect other forms of mis-speciﬁcation, for example, a missing variable showing spatial pattern (see McMillen 2003; Schaben-berger and Gotway 2005), or spatial heterogeneity.”
Spatial dependence and the representation of space in empirical models (2009, background): “ofthatamodellacksrepresentationofanimportanteconomicphenomenon. McMillen (2003) shows for example that spatial autocorrelation is often produced spuriously by model misspecification.”
The effect of species response form on species distribution model prediction and inference (2009, background): “The occurrence of SAC in model residuals caused by omission of important predictors has also been highlighted in spatial analysis literature (Cliff and Ord, 1981, p. 197; McMillen, 2003).”