Asymptotic Distributions of Quasi-Maximum Likelihood Estimators for Spatial Autoregressive Models

By Lung-fei Lee. 2004

1,052 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Epidemiology

View Paper: https://www.semanticscholar.org/paper/75066381cc929028209d5ffdf21194452a6eeb6f

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

In Epidemiology

Citations in the corpus

Inference on Higher-Order Spatial Autoregressive Models with Increasingly Many Parameters (2015, neutral): “…it is computationally simpler than procedures which may have better statistical properties, such as generalized method of moments (Kelejian and Prucha (1999) and Lee and Liu (2010)), optimal IV (Lee (2003)), Gaussian pseudo maximum likelihood (Lee (2004)), and adaptive estimation (Robinson (2010)).”
Semiparametric Estimation and Testing of Smooth Coefficient Spatial Autoregressive Models (2017, background): “At the same time, like in all these studies as well as many others (e.g., Kelejian & Prucha, 1998, 1999, 2010; Lee, 2004, 2007; Su & Jin, 2010; Su, 2012), the consistency of our estimator rests on an admittedly rather restrictive assumption of a correctly pre-specified spatial weighting matrix.”
Estimation of Sample Selection Models with Spatial Dependence (2012, methodology): “4 maximum likelihood (ML) to obtain asymptotically efficient estimates, including the SAE parameter, was suggested by Ord (1975) and rigorously analyzed by Lee (2004).”
Estimators of Binary Spatial Autoregressive Models: A Monte Carlo Study (2013, background): “The use of the weight matrix W implies that the spatial sites form a countable lattice (Lee, 2004), but part of the literature considers a continuous spatial index (Conley, 1999).”
Linear Spatial Dependence Models for Cross-Section Data (2014, methodology): “Kelejian and Prucha (1998, 1999) and Lee (2004) make the following assumptions to prove consistency of respectively the GMM estimator of the parameters in the SAR and SAC models and the ML estimator in the SAR model.”
Panel data models with spatially correlated error components (2007, background): “Lee ( 2004 ) also maintains a compactness assumption in deriving the asymptotic properties of the ML estimator for the spatial autoregressive parameter in a cross section framework .”
Large Panels with Common Factors and Spatial Correlation (2011, methodology): “Estimation of panels with spatially correlated errors can be based on maximum likelihood (ML) techniques (Lee (2004)), or on the generalized method of moments (GMM) (Kelejian and Prucha (1999); Lee (2007); Kelejian and Prucha (2009)).”
A test of cross section dependence for a linear dynamic panel model with regressors (2009, methodology): “Firstly we establish that SDIFX2 d ! 2hx (K+1) under the alternative of H1 : 6= 0, where SDIFX2 is dened in (28).”
Limit theorems for network dependent random variables (2019, background): “, Lauritzen (1996) and Pearl (2009); see also Chapter 19 of Murphy (2012) for applications in the literature of machine learning).”
Weak and Strong Cross Section Dependence and Estimation of Large Panels (2011, methodology): “…approaches to modelling cross section dependence in panels : (i) spatial processes pioneered by Whittle (1954) and developed further by Anselin (1988), Kelejian and Prucha (1999), and Lee (2004); and (ii) factor models introduced by Hotelling (1933) and rst applied in economics by Stone (1947).”
Network quantile autoregression (2019, background): “The model (2.2) is related to the autoregression models in spatial econometrics literature, e.g. Lee (2004); Lee and Yu (2009).”
On Two-Step Estimation of a Spatial Autoregressive Model with Autoregressive Disturbances and Endogenous Regressors (2013, background): “Estimation theory developed for the SARAR model typically assumed that — except for the spatial lag — the regressors are strictly exogenous; see, e.g., Kelejian and Prucha (1998, 1999, 2010) and Lee (2003, 2004, 2007).”
Identifying Peer Effects in Student Academic Achievement by Spatial Autoregressive Models with Group Unobservables (2010, background): “7 The estimation and properties of the SAR model have been studied in Anselin (1988), Kelejian and Prucha (1998, 1999), and Lee (2003, 2004, 2007a), among others.”
Estimation of spatial autoregressive panel data models with fixed effects (2010, methodology): “For the cross section SAR model with i.i.d. disturbances, Lee (2004) shows that when GnXnβ0 is asymptotically multicollinear with Xn, the information matrix is asymptotically singular and theMLEs ofβ0 andλ0will have a lower rate of convergence.”
An efficient GMM estimator of spatial autoregressive models (2010, background): “The other properties in Lemmas D.1–D.9 are either trivial or can be found in Lee (2001a, 2004, 2007).”