Title
Spatial Autoregression Model: Strong Consistency
Keywords
Spatial autoregression; Two-parameter martingale; Unit roots
Abstract
Let (α̂n,β̂n) denote the Gauss-Newton estimator of the parameter (α,β) in the autoregression model Zij=α Zi-1,j+βZi,j-1-αβ Zi-1,j-1+Eij. It is shown in an earlier paper that when α=β=1, {n3/2 (α̂n-α,β̂n-β)} converges in distribution to a bivariate normal random vector. A two-parameter strong martingale convergence theorem is employed here to prove that nr(α̂n-α, β̂n-β)→0̄ almost surely when r< 3/2. © 2003 Published by Elsevier Science B.V.
Publication Date
11-1-2003
Publication Title
Statistics and Probability Letters
Volume
65
Issue
2
Number of Pages
71-77
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.spl.2003.07.004
Copyright Status
Unknown
Socpus ID
0142153219 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0142153219
STARS Citation
Bhattacharyya, B. B.; Ren, J. J.; and Richardson, Gary D., "Spatial Autoregression Model: Strong Consistency" (2003). Scopus Export 2000s. 1536.
https://stars.library.ucf.edu/scopus2000/1536