A simultaneous spatial autoregressive model for compositional data - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Spatial Economic Analysis Année : 2021

A simultaneous spatial autoregressive model for compositional data

Thi-Huong-An Nguyen
  • Fonction : Auteur
Christine Thomas-Agnan
  • Fonction : Auteur
Thibault Laurent
  • Fonction : Auteur
Anne Ruiz-Gazen
  • Fonction : Auteur
Chakir Raja
  • Fonction : Auteur
Anna Lungarska

Résumé

In an election, the vote shares by party for a given subdivision of a territory form a compositional vector (positive components adding up to 1). Conventional multiple linear regression models are not adapted to explain this composition due to the constraint on the sum of the components and the potential spatial autocorrelation across territorial units. We develop a simultaneous spatial autoregressive model for compositional data that allows for both spatial correlation and correlations across equations. Using simulations and a data set from the 2015 French departmental election, we illustrate its estimation by two-stage and three-stage least squares methods.

Dates et versions

hal-03239250 , version 1 (27-05-2021)

Identifiants

Citer

Thi-Huong-An Nguyen, Christine Thomas-Agnan, Thibault Laurent, Anne Ruiz-Gazen, Chakir Raja, et al.. A simultaneous spatial autoregressive model for compositional data. Spatial Economic Analysis, 2021, vol. 16 (n° 2), pp.161-175. ⟨10.1080/17421772.2020.1828613⟩. ⟨hal-03239250⟩

Collections

ANR
41 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More