• Bernoulli
  • Volume 12, Number 3 (2006), 403-429.

Gaussian maximum likelihood estimation for ARMA models II: Spatial processes

Qiwei Yao and Peter J. Brockwell

Full-text: Open access


This paper examines the Gaussian maximum likelihood estimator (GMLE) in the context of a general form of spatial autoregressive and moving average (ARMA) processes with finite second moment. The ARMA processes are supposed to be causal and invertible under the half-plane unilateral order, but not necessarily Gaussian. We show that the GMLE is consistent. Subject to a modification to confine the edge effect, it is also asymptotically distribution-free in the sense that the limit distribution is normal, unbiased and has variance depending only on the autocorrelation function. This is an analogue of Hannan's classic result for time series in the context of spatial processes.

Article information

Bernoulli, Volume 12, Number 3 (2006), 403-429.

First available in Project Euclid: 28 June 2006

Permanent link to this document

Digital Object Identifier

Zentralblatt MATH identifier

ARMA spatial process asymptotic normality Gaussian maximum likelihood estimator martingale difference


Yao, Qiwei; Brockwell, Peter J. Gaussian maximum likelihood estimation for ARMA models II: Spatial processes. Bernoulli 12 (2006), no. 3, 403--429. doi:10.3150/bj/1151525128.

Export citation


  • [1] Besag, J. (1974) Spatial interaction and the statistical analysis of lattice systems (with discussion). J. Roy. Statist. Soc. Ser. B, 36, 192-236.
  • [2] Besag, J. (1975) Statistical analysis of non-lattice data. The Statistician, 24, 179-195.
  • [3] Brockwell, P.J. and Davis, R.A. (1991) Time Series: Theory and Methods, 2nd edn. New York: Springer-Verlag.
  • [4] Cressie, N.A.C. (1993) Statistics for Spatial Data. New York: Wiley.
  • [5] Dahlhaus, R. and Künsch, H. (1987) Edge effects and efficient parameter estimation for stationary random fields. Biometrika, 74, 877-882.
  • [6] Goodman, D. (1977) Some stability properties of two-dimensional linear shift-invariant digital filters. IEEE Trans. Circuits Systems, CAS-24, 201-208.
  • [7] Guyon, X. (1982) Parameter estimation for a stationary process on a d-dimensional lattice. Biometrika, 69, 95-105.
  • [8] Guyon, X. (1995) Random Fields on a Network. New York: Springer-Verlag.
  • [9] Hannan, E.J. (1973) The asymptotic theory of linear time-series models. J. Appl. Probab., 10, 130-145.
  • [10] Helson, H. and Lowdenslager, D. (1958) Prediction theory and Fourier series in several variables. Acta Math., 99, 165-201.
  • [11] Huang, D. and Anh, V.V. (1992) Estimation of spatial ARMA models. Austral. J. Statist., 34, 513-530.
  • [12] Justice, J.H. and Shanks, J.L. (1973) Stability criterion for N-dimensional digital filters. IEEE Trans. Automat. Control, AC-18, 284-286.
  • [13] Perera, G. (2001) Random fields on Zd, limit theorems and irregular sets. In M. Moore (ed.), Spatial Statistics: Methodological Aspects and Applications, Lecture Notes in Statist. 159, pp. 57-82. New York: Springer-Verlag.
  • [14] Shiryayev, A.N. (1984) Probability. New York: Springer-Verlag.
  • [15] Strintzis, M.G. (1977) Tests of stability of multidimensional filters. IEEE Trans. Circuits Systems, CAS-24, 432-437.
  • [16] Tjøstheim, D. (1978) Statistical spatial series modelling. Adv. in Appl. Probab., 10, 130-154.
  • [17] Tjøstheim, D. (1983) Statistical spatial series modelling II: Some further results in unilateral processes. Adv. in Appl. Probab., 15, 562-584.
  • [18] Whittle, P. (1954) On stationary processes in the plane. Biometrika, 41, 434-449.
  • [19] Wood, A.T.A. and Chan, G. (1994) Simulation of stationary Gaussian processes in [0, 1]d. J. Comput. Graph. Statist., 3, 409-432.
  • [20] Yao, Q. and Brockwell, P.J. (2005) Gaussian maximum likelihood estimation for ARMA models I: Time series. Revised for J. Time Ser. Anal.