Comparer des méthodes

	Régression Géographiquement Pondérée Multiscale (MGWR)	Modèle d'erreur spatiale (SEM)
Domaine	Analyse spatiale	Analyse spatiale
Famille	Regression model	Regression model
Année d'origine	2017	1988
Auteur d'origine	A. Stewart Fotheringham, Wei Yang, and Wei Kang	Anselin
Type	Local spatial regression	Spatial regression (spatially autocorrelated errors)
Source fondatrice	Fotheringham, A. S., Yang, W., & Kang, W. (2017). Multiscale geographically weighted regression (MGWR). Annals of the American Association of Geographers, 107(6), 1247-1265.	Anselin, L. (1988). Spatial Econometrics: Methods and Models. Kluwer Academic.
Alias	MGWR, multiscale GWR, multi-scale geographically weighted regression, variable-bandwidth GWR	SEM, spatial error regression, spatial autoregressive error model, Uzamsal Hata Modeli (SEM / Spatial Error)
Apparentées	5	5
Résumé	Multiscale Geographically Weighted Regression (MGWR) is a local spatial regression framework that relaxes the single-bandwidth constraint of standard GWR by allowing each predictor to operate at its own spatial scale. Each coefficient surface is calibrated with its own bandwidth, enabling the model to distinguish drivers that vary slowly across space from those that vary sharply.	The Spatial Error Model, developed within Anselin's spatial econometrics framework (1988), is a regression model that assumes spatial dependence enters through the error term: the disturbances of neighbouring units are correlated. It is used when unobserved shared factors make the errors of nearby observations move together, and it is estimated by maximum likelihood or GMM rather than ordinary least squares.