About predictions in spatial autoregressive models: optimal and almost optimal strategies. Issue 2 (3rd July 2017)

• Record Type: Journal Article
• Authors: Goulard, Michel; Laurent, Thibault; Thomas-Agnan, Christine
• Is Part Of: Spatial economic analysis. Volume 12:Issue 2/3(2017)
• Page Start: 304
• Page End: 325
• Publication Date: 2017-07-03
• Subjects: spatial simultaneous autoregressive models -- out-of-sample prediction -- best linear unbiased prediction (BLUP); 空间连立自回规模型 -- 样本外预测 -- 最佳线性无偏误预测（BLUP）; modèles autorégressifs spatiaux simultanés -- prédictions hors échantillon -- meilleurs prédicteurs linéaires sans biais (BLUP); modelos espaciales autorregresivos simultáneos -- predicción fuera de muestra -- mejor predicción lineal no sesgada (BLUP); C21 -- C53; Space in economics -- Periodicals; Economic geography -- Periodicals; Space in economics -- Econometric models -- Periodicals; Urbanization -- Periodicals; Espace (Économie politique) -- Périodiques; Économétrie -- Périodiques; Géographie économique -- Périodiques; Économie industrielle -- Périodiques; Économie du travail -- Périodiques; Économie urbaine -- Périodiques; Politique économique -- Périodiques; Relations économiques internationales -- Périodiques; 330.9
• DOI: 10.1080/17421772.2017.1300679
• Languages: English
• ISSNs: 1742-1772

Abstract

ABSTRACT: About predictions in spatial autoregressive models: optimal and almost optimal strategies. Spatial Economic Analysis . This paper addresses the problem of prediction in the spatial autoregressive (SAR) model for areal data, which is classically used in spatial econometrics. With kriging theory, prediction using the best linear unbiased predictors (BLUPs) is at the heart of the geostatistical literature. From a methodological point of view, we explore the limits of the extension of BLUP formulas in the context of SAR models for out-of-sample prediction simultaneously at several sites. We propose a more tractable 'almost best' alternative and clarify the relationship between the BLUP and a proper expectation–maximization (EM) algorithm predictor. From an empirical perspective, we present data-based simulations to compare the efficiency of classical formulas with the best and almost best predictions.