Extended Generalized Skew Laplace Random Field: Spatial Autoregressive and Moving Average Model for Prediction of Missing Data in Skew and Heavy Tailed Data

Document Type : Original Research Articles

Authors
Mohammad Mehdi Saber 1
Alireza Nematollahi 2
Mohsen Mohammadzadeh 3
1 1 Department of Statistics, Higher Education Center of Eghlid, Eghlid, Islamic Republic of Iran
2 2 Department of Statistics, Faculty of Sciences, Shiraz University, Shiraz, Islamic Republic of Iran
3 3 Department of Statistics, Faculty of Sciences, Tarbiat Modares University, Tehran, Islamic Republic of Iran
10.22059/jsciences.2021.315726.1007606
Abstract
In this paper, we define a spatial skew and heavy-tailed random field by an extended version of multivariate generalized skew Laplace distribution. The Bayesian spatial regression model is developed to explain the spatial data. A simulation study is then carried out to validate and evaluate the performance of the proposed model. The application of this model is also demonstrated in an analysis of a geological real data set.
Keywords
Multivariate generalized skew Laplace distribution
SARMA model
MCMC algorithm
  1. Anselin L. Spatial Econometrics, methods and models (Kluwer, Dordrecht) 1988.
  2. Anselin L. Spatial dependence and spatial structural instability in applied regression analysis. J Region Sci. 1990; 30: 185-207.
  3. Bustos O, Ojeda S and Vallejos R. Spatial ARMA models and its applications to image filtering. Brazil J Probab Stat. 2009; (23) 2: 141–165.
  4. Shin DW and Sarkar S. Parameter estimation in regression models with auto-correlated errors using irregular data. Commun Stat Theory Methods. 1994; 23: 3567-3580.
  5. Dogan O. Heteroskedasticity of unknown form in spatial autoregressive models with a moving average disturbance term. Econometrics. 2015; 3: 101-127.
  6. Oh M, Shin DW and Kim HJ. Bayesian analysis of regression models with spatially correlated errors and missing observations. Comput Stat Data Analys. 2002; 39: 387-400.
  7. Basu S and Reinsel GC. Regression models with spatially correlated errors. J Am Stat Assoc. 1994; 89: 88-99.
  8. Kim H-M and Mallick BA. Bayesian prediction using the skew Gaussian distribution. J Stat Plan Infer. 2004; 120: 85-101.
  9.  

 
  • Karimi O and Mohammadzadeh M. Bayesian spatial regression models with CSN correlated errors and missing observations. Stat Papers. 2012; 53: 205-218.
  • Saber MM, Nematollahi AR and Mohammadzadeh M. Generalized asymmetric Laplace random fields: existence and application. J Data Sci. 2018; 18: 51-68.
  • Kozubowski TJ, Podgórski K and Rychlik I. Multivariate generalized Laplace distribution and related random fields. J Multivar Analys. 2013; 113: 59–72.
  • Saber MM, Nematollahi AR and Mohammadzadeh M. Generalized Skew Laplace Random Fields: Bayesian Spatial Prediction for Skew and Heavy Tailed Data. J Stat Theory Appl, In Press.
  • Farzammehr MA, Zadkarami MR, McLachlan GJ and Lee SX. Skew-normal Bayesian spatial heterogeneity panel data models. J Appl Stat. 2020; 47(5): 804-826.
  • Kotz S, Kozubowski TJ and Podgórski K. The Laplace Distribution and Generalizations: A Revisit with Applications to Communications, Economics, Engineering and Finance, Birkhäuser, Boston 2001.
Journal of Sciences, Islamic Republic of Iran
Volume 32, Issue 2
Spring 2021
Pages 169-178