Skip to main content
placeholder image

The SAR model for very large datasets: a reduced rank approach

Journal Article


Download full-text (Open Access)

Abstract


  • The SAR model is widely used in spatial econometrics to model Gaussian processes on a discrete spatial lattice, but for large datasets, fitting it becomes computationally prohibitive, and hence, its usefulness can be limited. A computationally-efficient spatial model is the spatial random effects (SRE) model, and in this article, we calibrate it to the SAR model of interest using a generalisation of the Moran operator that allows for heteroskedasticity and an asymmetric SAR spatial dependence matrix. In general, spatial data have a measurement-error component, which we model, and we use restricted maximum likelihood to estimate the SRE model covariance parameters; its required computational time is only the order of the size of the dataset. Our implementation is demonstrated using mean usual weekly income data from the 2011 Australian Census.

Publication Date


  • 2015

Citation


  • Burden, S., Cressie, N. & Steel, D. G. (2015). The SAR model for very large datasets: a reduced rank approach. Econometrics, 3 (2), 317-338.

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=6436&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/5408

Number Of Pages


  • 21

Start Page


  • 317

End Page


  • 338

Volume


  • 3

Issue


  • 2

Place Of Publication


  • United Kingdom

Abstract


  • The SAR model is widely used in spatial econometrics to model Gaussian processes on a discrete spatial lattice, but for large datasets, fitting it becomes computationally prohibitive, and hence, its usefulness can be limited. A computationally-efficient spatial model is the spatial random effects (SRE) model, and in this article, we calibrate it to the SAR model of interest using a generalisation of the Moran operator that allows for heteroskedasticity and an asymmetric SAR spatial dependence matrix. In general, spatial data have a measurement-error component, which we model, and we use restricted maximum likelihood to estimate the SRE model covariance parameters; its required computational time is only the order of the size of the dataset. Our implementation is demonstrated using mean usual weekly income data from the 2011 Australian Census.

Publication Date


  • 2015

Citation


  • Burden, S., Cressie, N. & Steel, D. G. (2015). The SAR model for very large datasets: a reduced rank approach. Econometrics, 3 (2), 317-338.

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=6436&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/5408

Number Of Pages


  • 21

Start Page


  • 317

End Page


  • 338

Volume


  • 3

Issue


  • 2

Place Of Publication


  • United Kingdom