Penalized maximum likelihood estimation and variable selection in geostatistics
From MaRDI portal
Abstract: We consider the problem of selecting covariates in spatial linear models with Gaussian process errors. Penalized maximum likelihood estimation (PMLE) that enables simultaneous variable selection and parameter estimation is developed and, for ease of computation, PMLE is approximated by one-step sparse estimation (OSE). To further improve computational efficiency, particularly with large sample sizes, we propose penalized maximum covariance-tapered likelihood estimation (PMLE) and its one-step sparse estimation (OSE). General forms of penalty functions with an emphasis on smoothly clipped absolute deviation are used for penalized maximum likelihood. Theoretical properties of PMLE and OSE, as well as their approximations PMLE and OSE using covariance tapering, are derived, including consistency, sparsity, asymptotic normality and the oracle properties. For covariance tapering, a by-product of our theoretical results is consistency and asymptotic normality of maximum covariance-tapered likelihood estimates. Finite-sample properties of the proposed methods are demonstrated in a simulation study and, for illustration, the methods are applied to analyze two real data sets.
Recommendations
- Variable selection in spatial regression via penalized least squares
- Covariance tapering for likelihood-based estimation in large spatial data sets
- On Selection of Spatial Linear Models for Lattice Data
- Estimating spatial covariance using penalised likelihood with weightedL1penalty
- Variable selection for binary spatial regression: penalized quasi-likelihood approach
Cites work
- Covariance tapering for likelihood-based estimation in large spatial data sets
- Fixed-domain asymptotic properties of tapered maximum likelihood estimators
- scientific article; zbMATH DE number 4088698 (Why is no real title available?)
- scientific article; zbMATH DE number 52492 (Why is no real title available?)
- scientific article; zbMATH DE number 1156422 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Interpolation of spatial data. Some theory for kriging
- Least angle regression. (With discussion)
- Maximum likelihood estimation of models for residual covariance in spatial regression
- Nonconcave penalized likelihood with a diverging number of parameters.
- One-step sparse estimates in nonconcave penalized likelihood models
- Optimal Geostatistical Model Selection
- Penalized maximum likelihood estimation and variable selection in geostatistics
- Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree
- Statistical Methods for Spatial Data Analysis
- The Adaptive Lasso and Its Oracle Properties
- Tuning parameter selectors for the smoothly clipped absolute deviation method
- Variable selection in spatial regression via penalized least squares
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(30)- Variable selection for spatial Poisson point processes via a regularization method
- Variable selection for spatial semivarying coefficient models
- Semiparametric method and theory for continuously indexed spatio-temporal processes
- Spatio-temporal expanding distance asymptotic framework for locally stationary processes
- High dimensional classification for spatially dependent data with application to neuroimaging
- Non-separable models with high-dimensional data
- Variable selection in spatial regression via penalized least squares
- On selection of spatial linear models for lattice data
- scientific article; zbMATH DE number 7370554 (Why is no real title available?)
- Variable selection of partially linear varying coefficient spatial autoregressive model
- GEE-Assisted Forward Regression for Spatial Latent Variable Models
- Penalized Lq-likelihood estimators and variable selection in linear regression models
- Gradient Extrapolated Stochastic Kriging
- Variable selection for binary spatial regression: penalized quasi-likelihood approach
- Automatic variable selection for semiparametric spatial autoregressive model
- Estimation of the Spatial Weighting Matrix for Spatiotemporal Data under the Presence of Structural Breaks
- Binary response models for heterogeneous panel data with interactive fixed effects
- Recognition and variable selection in sparse spatial panel data models with fixed effects
- Regularized nonlinear regression with dependent errors and its application to a biomechanical model
- Penalized maximum likelihood estimation and variable selection in geostatistics
- On estimation and prediction of geostatistical regression models via a corrected Stein's unbiased risk estimator
- Multikernel linear mixed model with adaptive Lasso for complex phenotype prediction
- Penalized Lq-likelihood estimator and its influence function in generalized linear models
- Variable selection in multivariate linear regression model for spatially dependent data
- Penalty free variable selection for high-dimensional linear models
- EM algorithm for generalized ridge regression with spatial covariates
- A review of regularised estimation methods and cross-validation in spatiotemporal statistics
- On maximizing the likelihood function of general geostatistical models
- Spatial regression with multiplicative errors, and its application with LiDAR measurements
- A multi-resolution approximation via linear projection for large spatial datasets
This page was built for publication: Penalized maximum likelihood estimation and variable selection in geostatistics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q661173)
