Nonstationary covariance modeling for incomplete data: Monte Carlo EM approach

A multi-resolution basis can provide a useful representation of nonstationary two-dimensional spatial processes that are typically encountered in the geosciences. The main advantages are its flexibility for representing departures from stationarity and importantly the scalability of algorithms to large numbers of spatial locations. The key ingredients of our approach are the availability of fast transforms for wavelet bases on regular grids and enforced sparsity in the covariance matrix among wavelet basis coefficients. In support of this approach we outline a theoretical proposition for decay properties of the multi-resolution covariance for mixtures of Matern covariances. A covariance estimator, built upon a regularized method of moment, is straightforward to compute for complete data on regular grids. For irregular spatial data the estimator is implemented by using a conditional simulation algorithm drawn from a Monte Carlo Expectation Maximization approach, to translate the problem to a regular grid in order to take advantage of efficient wavelet transforms. This method is illustrated with a Monte Carlo experiment and applied to surface ozone data from an environmental monitoring network. The computational efficiency makes it possible to provide bootstrap measures of uncertainty and these provide objective evidence of the nonstationarity of the surface ozone field.

[1]  S. Mallat,et al.  Adaptive covariance estimation of locally stationary processes , 1998 .

[2]  Roger Woodard,et al.  Interpolation of Spatial Data: Some Theory for Kriging , 1999, Technometrics.

[3]  Douglas W. Nychka,et al.  Statistical models for monitoring and regulating ground‐level ozone , 2005 .

[4]  D. Higdon.  Space and Space-Time Modeling using Process Convolutions , 2002 .

[5]  D. Nychka,et al.  Covariance Tapering for Interpolation of Large Spatial Datasets , 2006 .

[6]  Noel A Cressie,et al.  Combining regional climate model output via a multivariate Markov random field model , 2007 .

[7]  M. Stein,et al.  Estimating deformations of isotropic Gaussian random fields on the plane , 2008, 0804.0723.

[8]  N. Cressie,et al.  Combining Ensembles of Regional Climate Model Output via a Multivariate Markov Random Field Model , 2008 .

[9]  Yazhen Wang.  Function estimation via wavelet shrinkage for long-memory data , 1996 .

[10]  A. Wood,et al.  Simulation of Stationary Gaussian Processes in [0, 1] d , 1994 .

[11]  Noureddine El Karoui,et al.  Operator norm consistent estimation of large-dimensional sparse covariance matrices , 2008, 0901.3220.

[12]  Christopher J Paciorek,et al.  Spatial modelling using a new class of nonstationary covariance functions , 2006, Environmetrics.

[13]  J. Andrew Royle,et al.  Multiresolution models for nonstationary spatial covariance functions , 2002 .

[14]  L. Shepp,et al.  A Statistical Model for Positron Emission Tomography , 1985 .

[15]  Klaus Nordhausen,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman , 2009 .

[16]  Montserrat Fuentes,et al.  A New Class of Nonstationary Spatial Models , 2001 .

[17]  Amara Lynn Graps,et al.  An introduction to wavelets , 1995 .

[18]  J. D. Wilson,et al.  A smoothed EM approach to indirect estimation problems, with particular reference to stereology and emission tomography , 1990 .

[19]  A.H. Tewfik,et al.  Correlation structure of the discrete wavelet coefficients of fractional Brownian motion , 1992, IEEE Trans. Inf. Theory.

[20]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[21]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[22]  P. Bickel,et al.  Regularized estimation of large covariance matrices , 2008, 0803.1909.

[23]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[24]  I. Johnstone.  WAVELET SHRINKAGE FOR CORRELATED DATA AND INVERSE PROBLEMS: ADAPTIVITY RESULTS , 1999 .

[25]  G. C. Wei,et al.  A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms , 1990 .

[26]  P. Guttorp,et al.  Nonparametric Estimation of Nonstationary Spatial Covariance Structure , 1992 .

[27]  Jean-Paul Chilès,et al.  Wiley Series in Probability and Statistics , 2012 .

[28]  E. Thompson,et al.  Monte Carlo estimation of variance component models for large complex pedigrees. , 1991, IMA journal of mathematics applied in medicine and biology.

[29]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing, 2nd Edition , 1999 .

[30]  Montserrat Fuentes,et al.  A high frequency kriging approach for non‐stationary environmental processes , 2001 .

[31]  D. Donoho.  Nonlinear Solution of Linear Inverse Problems by Wavelet–Vaguelette Decomposition , 1995 .

[32]  David Higdon,et al.  Non-Stationary Spatial Modeling , 2022, 2212.08043.

[33]  M. K. Kwong,et al.  W-matrices, nonorthogonal multiresolution analysis, and finite signals of arbitrary length , 1994 .

[34]  P. Bickel,et al.  Covariance regularization by thresholding , 2009, 0901.3079.