Testing for unit roots and cointegration in spatial cross-section data

Michael Beenstock, Dan Feldman, Daniel Felsenstein*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


Spatial impulses are derived for SAR models containing a spatial unit root. Analytical solutions are obtained for lateral space where the number of spatial units tends to infinity. Numerical solutions are obtained for finite regular lattices where edge-effects are shown to influence spatial impulses, and for irregular lattices. Monte Carlo simulation methods are used to compute critical values for spatial unit root tests in SAR models estimated from spatial cross-section data for regular and irregular lattices. We also compute critical SAC values for spatial cointegration tests for cross-section data that happen to be spatially nonstationary. We show that parameter estimates in spatially cointegrated models are 'superconsistent'.

Original languageAmerican English
Pages (from-to)203-222
Number of pages20
JournalSpatial Economic Analysis
Issue number2
StatePublished - Jun 2012


  • Spatial unit roots
  • spatial cointegration
  • spatial impulse responses


Dive into the research topics of 'Testing for unit roots and cointegration in spatial cross-section data'. Together they form a unique fingerprint.

Cite this