Startseite The stationary regions for the parameter space of unilateral second-order spatial AR model
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

The stationary regions for the parameter space of unilateral second-order spatial AR model

  • A. Mojiri , Y. Waghei EMAIL logo , H. R. Nili Sani und G. R. Mohtashami Borzadaran
Veröffentlicht/Copyright: 28. August 2018
Veröffentlichen auch Sie bei De Gruyter Brill

Abstract

The analysis of spatial models has received much attention in the last three decades. It involves methods which take into account the data location for exploring and modelling spatial data. Spatial modelling has its applications in many fields like geology, geography, agriculture, meteorology, economics etc. In this paper, the unilateral second-order spatial autoregressive model, denoted as SAR(2,1) model, is introduced. Then the necessary conditions for casual solutions of this model will be given. Since each casual model is a stationary model, these conditions will be stationary regions for the parameter space of the SAR(2,1) model. Under the stationary conditions, we can estimate the model parameters.

MSC 2010: 62M30; 91B72

Communicated by Nikolai Leonenko


Acknowledgements

The authors are grateful to the referees and the editor in chief of the journal “Random Operators and Stochastic Equations” for the comments that greatly improved this manuscript.

References

[1] S. Abdullah and M. Shitan, Some explicit conditions for a stationary representation of unilateral second-order spatial ARMA model, Pertanika J. Sci. Technol. 17 (2009), no. 1, 163–171. Suche in Google Scholar

[2] M. S. Bartlett, Physical nearest-neighbour models and non-linear time-series, J. Appl. Probab. 8 (1971), no. 2, 222–232. 10.2307/3211892Suche in Google Scholar

[3] S. Basu and G. C. Reinsel, A note on properties of spatial Yule–Walker estimators, J. Stat. Comput. Simul. 41 (1992), 243–255. 10.1080/00949652208811404Suche in Google Scholar

[4] S. Basu and G. C. Reinsel, Properties of the spatial unilateral first-order ARMA model, Adv. in Appl. Probab. 25 (1993), no. 3, 631–648. 10.2307/1427527Suche in Google Scholar

[5] S. Basu and G. C. Reinsel, Regression models with spatially correlated errors, J. Amer. Statist. Assoc. 89 (1994), no. 425, 88–99. 10.1080/01621459.1994.10476449Suche in Google Scholar

[6] J. Besag, Spatial interaction and the statistical analysis of lattice systems, J. Roy. Statist. Soc. Ser. B 36 (1974), no. 2, 192–236. 10.1111/j.2517-6161.1974.tb00999.xSuche in Google Scholar

[7] J. E. Besag and D. Higdon, Bayesian analysis of agricultural field experiments, J. Roy. Statist. Soc. Ser. B 61 (1999), no. 4, 691–746. 10.1111/1467-9868.00201Suche in Google Scholar

[8] B. B. Bhattacharyya, T. M. Khalil and G. D. Richardson, Gauss–Newton estimation of parameters for a spatial autoregression model, Statist. Probab. Lett. 28 (1996), no. 2, 173–179. 10.1016/0167-7152(95)00114-XSuche in Google Scholar

[9] O. H. Bustos, R. Fraiman and V. J. Yohai, Asymptotic behavior of the estimates based on residual autocovariances for ARMA models, Robust and Nonlinear Time Series Analysis, Springer, New York (1984), 26–49. 10.1007/978-1-4615-7821-5_3Suche in Google Scholar

[10] N. Cressie, Statistics for Spatial Data, John Wiley & Sons, New York, 1993. 10.1002/9781119115151Suche in Google Scholar

[11] B. R. Cullis and A. C. Gleeson, Spatial analysis of field experiments-an extension to two dimensions, Biometrics 47 (1991), 1449–1460. 10.2307/2532398Suche in Google Scholar

[12] M. Drapatz, Strictly stationary solutions of spatial ARMA equations, Ann. Inst. Statist. Math. 68 (2016), no. 2, 385–412. 10.1007/s10463-014-0500-ySuche in Google Scholar

[13] M. G. Genton and H. L. Koul, Minimum distance inference in unilateral autoregressive lattice processes, Statist. Sinica 18 (2008), 617–631. Suche in Google Scholar

[14] V. B. Goryainov, Least-modules estimates for spatial autoregression coefficients, J. Comput. Syst. Sci. Int. 50 (2011), no. 4, 565–572. 10.1134/S1064230711040101Suche in Google Scholar

[15] E. A. Grau, Robust estimation of autocorrelation parameters in the AR(1)×AR(1) model, PhD Thesis, North Carolina State University, 2000. Suche in Google Scholar

[16] S. G. Krantz, Function Theory of Several Complex Variables, 2nd ed., American Mathematical Society, Providence, 2001. 10.1090/chel/340Suche in Google Scholar

[17] N. Leonenko and E. Taufer, Disaggregation of spatial autoregressive processes, Spat. Stat. 3 (2013), 1–20. 10.1016/j.spasta.2013.01.001Suche in Google Scholar

[18] R. J. Martin, A subclass of lattice processes applied to a problem in planar sampling, Biometrika 66 (1979), no. 2, 209–217. 10.1093/biomet/66.2.209Suche in Google Scholar

[19] R. J. Martin, Some aspects of experimental design and analysis when errors are correlated, Biometrika 69 (1982), no. 3, 597–612. 10.1093/biomet/69.3.597Suche in Google Scholar

[20] R. J. Martin, The use of time-series models and methods in the analysis of agricultural field trials, Comm. Statist. Theory Methods 19 (1990), no. 1, 55–81. 10.1080/03610929008830187Suche in Google Scholar

[21] R. J. Martin, Some results on unilateral ARMA lattice processes, J. Statist. Plann. Inference 50 (1996), no. 3, 395–411. 10.1016/0378-3758(95)00066-6Suche in Google Scholar

[22] S. M. Ojeda, R. O. Vallejos and M. M. Lucini, Performance of robust RA estimator for bidimensional autoregressive models, J. Stat. Comput. Simul. 72 (2002), no. 1, 47–62. 10.1080/00949650211426Suche in Google Scholar

[23] S. M. Roknossadat and M. Zarepour, M-estimation for a spatial unilateral autoregressive model with infinite variance innovations, Econometric Theory 26 (2010), no. 6, 1663–1682. 10.1017/S0266466609990752Suche in Google Scholar

[24] S. M. Roknossadati and M. Zarepour, M-estimation for near unit roots in spatial autoregression with infinite variance, Statistics 45 (2011), no. 4, 337–348. 10.1080/02331881003768792Suche in Google Scholar

[25] M. Rosenblatt, Gaussian and Non-Gaussian Linear Time Series and Random Fields, Springer, New York, 2012. Suche in Google Scholar

[26] D. Tjostheim, Statistical spatial series modelling, Adv. in Appl. Probab. 10 (1978), no. 1, 130–154. 10.2307/1426722Suche in Google Scholar

[27] D. Tjostheim, Statistical spatial series modelling II: Some further results on unilateral lattice processes, Adv. in Appl. Probab. 15 (1983), no. 3, 562–584. 10.2307/1426619Suche in Google Scholar

[28] P. Whittle, On stationary processes in the plane, Biometrika 41 (1954), no. 3, 434–449. 10.1093/biomet/41.3-4.434Suche in Google Scholar

[29] Q. Yao and P. J. Brockwell, Gaussian maximum likelihood estimation for ARMA models II: Spatial processes, Bernoulli 12 (2006), no. 3, 403–429. 10.3150/bj/1151525128Suche in Google Scholar

Received: 2017-04-12
Accepted: 2018-05-02
Published Online: 2018-08-28
Published in Print: 2018-09-01

© 2018 Walter de Gruyter GmbH, Berlin/Boston

Heruntergeladen am 15.10.2025 von https://www.degruyterbrill.com/document/doi/10.1515/rose-2018-0017/html?lang=de
Button zum nach oben scrollen