Penalized maximum likelihood estimation and variable selection in geostatistics

TL;DR

This paper introduces penalized maximum likelihood methods with covariance tapering for variable selection in spatial linear models, providing theoretical guarantees and demonstrating effectiveness through simulations and real data applications.

Contribution

It develops novel penalized likelihood estimators with covariance tapering for efficient variable selection in geostatistics, along with their theoretical properties and practical performance.

Findings

Methods achieve consistency and sparsity.

Theoretical properties include asymptotic normality and oracle properties.

Simulation and real data analyses validate effectiveness.

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$_{\mathrm{T}}$) and its one-step sparse estimation (OSE$_{\mathrm{T}}$). 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$_{\mathrm{T}}$ and OSE$_{\mathrm{T}}$ 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.