The relative efficiencies of various predictors in spatial econometric models containing spatial lags

89 citations recorded by the source corpus.

How researchers see this paper

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

A Command for Estimating Spatial-Autoregressive Models with Spatial-Autoregressive Disturbances and Additional Endogenous Variables (2013, methodology): “The predictor computed by the option naive will generally be biased; see Kelejian and Prucha (2007) for an explanation.”
Thirty years of spatial econometrics (2010, background): “…are the generalization of the GMM estimators to models that include both spatial dependence and heteroscedasticity in Kelejian and Prucha (2010) and Arraiz et al. (2010), and the heteroscedastic and autocorrelation consistent (HAC) approach based on kernel estimation in Kelejian and Prucha (2007a).”
Spatial Panel-data Models Using Stata (2017, methodology): “15 As expected, even in the panel data case, numerical results are fully consistent with the theoretical notions reported in Kelejian and Prucha (2007): the biased naive predictor is the worst especially when ρ = λ = 0 .”
About predictions in spatial autoregressive models: optimal and almost optimal strategies (2017, methodology): “Hence, using a precision matrix version of Goldberger as we do is much easier than using a covariance matrix version of Goldberger as in Kelejian and Prucha (2007).”