A Spatial Durbin Model for Compositional Data

Tingting Huang (1) , Gilbert Saporta (2) , Huiwen Wang (1)

1 BUAA - Beihang University
2 CEDRIC - MSDMA - CEDRIC. Méthodes statistiques de data-mining et apprentissage

A compositional linear model (regression of a scalar response on a set of compositions) for areal data is proposed, where observations are not independent and present spatial autocorrelation. Specifically, we borrow thoughts from the spatial Durbin model considering that it produces unbiased coefficient estimates compared to other spatial linear regression models (including the spatial error model, the spatial autoregressive model, the Kelejian-Prucha model, and the spatial Durbin error model). The orthonormal log-ratio (olr) transformation based on a sequential binary partition of compositions and maximum likelihood estimation method are employed to estimate the new model. We also check the proposed estimators on a simulated and a real dataset.

Mots clés: compositional data; spatial Durbin model; spatial autoregressive model

Domaines: Statistiques [stat]

Tingting Huang, Gilbert Saporta, Huiwen Wang. A Spatial Durbin Model for Compositional Data. Daouia A., Ruiz-Gazen A. Advances in Contemporary Statistics and Econometrics, Springer Nature, pp.471-488, 2021, 978-3-030-73249-3. ⟨10.1007/978-3-030-73249-3_24⟩. ⟨hal-03274385⟩