Asymptotic theory of generalized information criterion for geostatistical regression model selection

DOI10.1214/14-AOS1258zbMATH Open1302.62203arXiv1412.0836OpenAlexW1999487741MaRDI QIDQ482898FDOQ482898

Authors: Chih-Hao Chang, Hsin-Cheng Huang, Ching-Kang Ing 

Publication date: 6 January 2015

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Information criteria, such as Akaike's information criterion and Bayesian information criterion are often applied in model selection. However, their asymptotic behaviors for selecting geostatistical regression models have not been well studied, particularly under the fixed domain asymptotic framework with more and more data observed in a bounded fixed region. In this article, we study the generalized information criterion (GIC) for selecting geostatistical regression models under a more general mixed domain asymptotic framework. Via uniform convergence developments of some statistics, we establish the selection consistency and the asymptotic loss efficiency of GIC under some regularity conditions, regardless of whether the covariance model is correctly or wrongly specified. We further provide specific examples with different types of explanatory variables that satisfy the conditions. For example, in some situations, GIC is selection consistent, even when some spatial covariance parameters cannot be estimated consistently. On the other hand, GIC fails to select the true polynomial order consistently under the fixed domain asymptotic framework. Moreover, the growth rate of the domain and the degree of smoothness of candidate regressors in space are shown to play key roles for model selection.

Full work available at URL: https://arxiv.org/abs/1412.0836

Recommendations

• Consistency of a Class of Information Criteria for Model Selection in Nonlinear Regression
• Dependence of Bayesian model selection criteria and Fisher information matrix on sample size
• Convergence rates of the generalized information criterion
• A consistency property of the AIC for multivariate linear models when the dimension and the sample size are large
• Performance of information criteria for spatial models

zbMATH Keywords

variable selectionselection consistencyAkaike's information criterionBayesian information criterionfixed domain asymptoticincreasing domain asymptotic

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Asymptotic properties of parametric estimators (62F12) Inference from spatial processes (62M30) Statistical ranking and selection procedures (62F07) Applications of statistics to environmental and related topics (62P12) Geostatistics (86A32)

Cites Work

• Semiparametric Regression
• Fence methods for mixed model selection
• Estimating the dimension of a model
• Fixed-domain asymptotic properties of tapered maximum likelihood estimators
• Interpolation of spatial data. Some theory for kriging
• Random-Effects Models for Longitudinal Data
• On fixed-domain asymptotics and covariance tapering in Gaussian random field models
• Maximum likelihood estimation of models for residual covariance in spatial regression
• Towards reconciling two asymptotic frameworks in spatial statistics
• Spatial variation. 2nd ed
• Title not available (Why is that?)
• Asymptotic properties of criteria for selection of variables in multiple regression
• Title not available (Why is that?)
• Consistent procedures for mixed linear model selection
• Conditional Akaike information for mixed-effects models
• Asymptotic optimality for \(C_ p\), \(C_ L\), cross-validation and generalized cross-validation: Discrete index set
• Title not available (Why is that?)
• Selecting mixed-effects models based on a generalized information criterion
• Model selection in linear mixed models
• Consistent covariate selection and post model selection inference in semiparametric regression.
• Order selection for same-realization predictions in autoregressive processes
• Accumulated prediction errors, information criteria and optimal forecasting for autoregressive time series
• Asymptotic properties of a maximum likelihood estimator with data from a Gaussian process
• Uniform moment bounds of Fisher's information with applications to time series
• Title not available (Why is that?)
• Semiparametric regression model selections.
• Optimal Geostatistical Model Selection
• Asymptotic theory of generalized information criterion for geostatistical regression model selection

Cited In (7)

• A generalized measure of uncertainty in geostatistical model selection
• Optimal model average prediction in orthogonal kriging models
• Bayesian fixed-domain asymptotics for covariance parameters in a Gaussian process model
• Asymptotic theory of generalized information criterion for geostatistical regression model selection
• Composite likelihood estimation for a Gaussian process under fixed domain asymptotics
• Consistency of a Class of Information Criteria for Model Selection in Nonlinear Regression
• Model selection with misspecified spatial covariance structure

Uses Software

• SemiPar

This page was built for publication: Asymptotic theory of generalized information criterion for geostatistical regression model selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q482898)