IGB

Connexion

(Article of periodic en Anglais - 2014)

Document title

Estimation of autoregressive models with two types of weak spatial dependence by means of the W-based and the latent variables approach : evidence from Monte Carlo simulations

Authors(s) and Affiliation(s)

LIU A. (1) ; FOLMER H. (2) ; OUD J.H.L. (3) ;
(1) Dept. of Spatial Sciences, Univ., Groningen, PAYS-BAS
(2) Faculty of Spatial Sciences, Univ., Groningen, PAYS-BAS
(3) Behavioural Science Institute, Univ., Nijmegen, PAYS-BAS

Abstract

This article examines the estimation of autoregressive models with two types of weak spatial dependence by means of the W-based and the latent variables approach through evidence from Monte Carlo simulations. It starts by comparing the two approaches by means of simulations in terms of bias and root mean squared error (RMSE) for different values of the spatial lag parameters, specifications of the weights matrices, and sample sizes. The simulation results show that compared with the single W-based models, SEM frequently has smaller bias and RMSE. Furthermore, SEM even outperforms the correctly specified W-based models (based on the same two weights matrices used for data generation) in many cases

Source

Article of periodic

published at : Environment & planning A / ISSN 0308-518X

Editor : Pion, London - ROYAUME-UNI (1974)

Millesime : 2014, vol. 46, no1 [pp. 186-202]

Bibliographic references : 2 p.

Collation : 3 fig.

Language

Anglais

INIST-CNRS, Cote INIST : 15583 A

Digital Object Identifier

Go to electronic document thanks to its DOI : doi:10.1068/a45558

Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI), 2014
Refdoc record number (ud4) : 28163810 : Permanent link - XML version
Powered by Pxxo