eprintid: 15788 rev_number: 19 eprint_status: archive userid: 1482 importid: 105 dir: disk0/00/01/57/88 datestamp: 2014-07-09 17:40:31 lastmod: 2021-04-02 15:48:23 status_changed: 2017-05-04 14:30:59 type: monograph metadata_visibility: no_search creators_name: Thomas-Agnan, Christine creators_name: Laurent, Thibault creators_name: Goulard, Michel creators_idrefppn: 076657833 creators_affiliation: Toulouse School of Economics creators_affiliation: Toulouse School of Economics creators_affiliation: INRA, UMR 1201 DYNAFOR, Chemin de Borde Rouge BP52627, F31326 Castanet-Tolosan, France). title: About predictions in spatial autoregressive models ispublished: pub subjects: subjects_ECO abstract: We address the problem of prediction in the spatial autoregressive SAR model for areal data which is classically used in spatial econometrics. With the Kriging theory, prediction using Best Linear Unbiased Predictors is at the heart of the geostatistical literature. From the methodological point of view, we explore the limits of the extension of BLUP formulas in the context of the spatial autoregressive 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 EM-algorithm predictor. From an empirical perspective, we present data-based simulations to compare the efficiency of the classical formulas with the best and almost best predictions. date: 2014-09-25 date_type: published publisher: TSE Working Paper official_url: http://tse-fr.eu/pub/27788 sub_title: Optimal and almost optimal strategies faculty: tse divisions: tse keywords: Spatial simultaneous autoregressive models keywords: out of sample prediction keywords: best linear unbiased prediction language: fr has_fulltext: TRUE view_date_year: 2014 full_text_status: public monograph_type: working_paper series: TSE Working Paper volume: 13-452 place_of_pub: Toulouse pages: 19 institution: Université Toulouse 1 Capitole department: Toulouse School of Economics book_title: TSE Working Paper oai_identifier: oai:tse-fr.eu:27788 harvester_local_overwrite: department harvester_local_overwrite: date harvester_local_overwrite: faculty harvester_local_overwrite: site harvester_local_overwrite: pages harvester_local_overwrite: place_of_pub harvester_local_overwrite: institution harvester_local_overwrite: creators_affiliation harvester_local_overwrite: creators_idrefppn oai_lastmod: 2017-04-21T08:44:08Z oai_set: tse site: ut1 citation: Thomas-Agnan, Christine , Laurent, Thibault and Goulard, Michel (2014) About predictions in spatial autoregressive models : Optimal and almost optimal strategies. TSE Working Paper, n. 13-452, Toulouse document_url: https://publications.ut-capitole.fr/id/eprint/15788/1/Laurent_15788.pdf