arXiv subjects

Joseph Guinness

Publications and source records attributed to Joseph Guinness.

35 records · Page 2Linked to original sources

arXiv2019

Efficient Computation of Gaussian Likelihoods for Stationary Markov Random Field Models

Rue and Held (2005) proposed a method for efficiently computing the Gaussian likelihood for stationary Markov random field models, when the data locations fall on a complete regular grid, and the model has no additive error term. The calculations rely on the availability of the covariances. We prove a theorem giving the rate of convergence of a spectral method of computing the covariances, establishing that the error decays faster than any polynomial in the size of the computing grid. We extend the exact likelihood calculations to the case of non-rectangular domains and missing values on the interior of the grid and to the case when an additive uncorrelated error term (nugget) is present in the model. We also give an alternative formulation of the likelihood that has a smaller memory burden, parts of which can be computed in parallel. We show in simulations that using the exact likelihood can give far better parameter estimates than using standard Markov random field approximations. Having access to the exact likelihood allows for model comparisons via likelihood ratios on large datasets, so as an application of the methods, we compare several state-of-the-art methods for large spatial datasets on an aerosol optical thickness dataset. We find that simple block independent likelihood and composite likelihood methods outperform stochastic partial differential equation approximations in terms of computation time and returning parameter estimates that nearly maximize the likelihood.

stat.CO↗

arXiv2019

A general framework for Vecchia approximations of Gaussian processes

Gaussian processes (GPs) are commonly used as models for functions, time series, and spatial fields, but they are computationally infeasible for large datasets. Focusing on the typical setting of modeling data as a GP plus an additive noise term, we propose a generalization of the Vecchia (1988) approach as a framework for GP approximations. We show that our general Vecchia approach contains many popular existing GP approximations as special cases, allowing for comparisons among the different methods within a unified framework. Representing the models by directed acyclic graphs, we determine the sparsity of the matrices necessary for inference, which leads to new insights regarding the computational properties. Based on these results, we propose a novel sparse general Vecchia approximation, which ensures computational feasibility for large spatial datasets but can lead to considerable improvements in approximation accuracy over Vecchia's original approach. We provide several theoretical results and conduct numerical comparisons. We conclude with guidelines for the use of Vecchia approximations in spatial statistics.

stat.ME↗

arXiv2019

Spectral Density Estimation for Random Fields via Periodic Embeddings

We introduce methods for estimating the spectral density of a random field on a $d$-dimensional lattice from incomplete gridded data. Data are iteratively imputed onto an expanded lattice according to a model with a periodic covariance function. The imputations are convenient computationally, in that circulant embedding and preconditioned conjugate gradient methods can produce imputations in $O(n\log n)$ time and $O(n)$ memory. However, these so-called periodic imputations are motivated mainly by their ability to produce accurace spectral density estimates. In addition, we introduce a parametric filtering method that is designed to reduce periodogram smoothing bias. The paper contains theoretical results studying properties of the imputed data periodogram and numerical and simulation studies comparing the performance of the proposed methods to existing approaches in a number of scenarios. We present an application to a gridded satellite surface temperature dataset with missing values.

stat.ME↗

arXiv2019

Geostatistical Modeling of Positive Definite Matrices: An Application to Diffusion Tensor Imaging

Geostatistical modeling for continuous point-referenced data has been extensively applied to neuroimaging because it produces efficient and valid statistical inference. However, diffusion tensor imaging (DTI), a neuroimaging characterizing the brain structure produces a positive definite (p.d.) matrix for each voxel. Current geostatistical modeling has not been extended to p.d. matrices because introducing spatial dependence among positive definite matrices properly is challenging. In this paper, we use the spatial Wishart process, a spatial stochastic process (random field) where each p.d. matrix-variate marginally follows a Wishart distribution, and spatial dependence between random matrices is induced by latent Gaussian processes. This process is valid on an uncountable collection of spatial locations and is almost surely continuous, leading to a reasonable means of modeling spatial dependence. Motivated by a DTI dataset of cocaine users, we propose a spatial matrix-variate regression model based on the spatial Wishart process. A problematic issue is that the spatial Wishart process has no closed-form density function. Hence, we propose approximation methods to obtain a feasible working model. A local likelihood approximation method is also applied to achieve fast computation. The simulation studies and real data analysis demonstrate that the working model produces reliable inference and improved performance compared to other methods.

stat.ME↗

arXiv2019

Mean-dependent nonstationary spatial models

Nonstationarity is a major challenge in analyzing spatial data. For example, daily precipitation measurements may have increased variability and decreased spatial smoothness in areas with high mean rainfall. Common nonstationary covariance models introduce parameters specific to each location, giving a highly-parameterized model which is difficult to fit. We develop a nonstationary spatial model that uses the mean to determine the covariance in a region, resulting in a far simpler, albeit more specialized, model. We explore inferential and predictive properties of the model under various simulated data situations. We show that this model in certain circumstances improves predictions compared to a standard stationary spatial model. We further propose a computationally efficient approximation that has comparable predictive accuracy. We also develop a test for nonstationary data and show it reliably identifies nonstationarity. We apply these methods to daily precipitation in Puerto Rico.

stat.ME↗

arXiv2019

Gaussian Process Learning via Fisher Scoring of Vecchia's Approximation

We derive a single pass algorithm for computing the gradient and Fisher information of Vecchia's Gaussian process loglikelihood approximation, which provides a computationally efficient means for applying the Fisher scoring algorithm for maximizing the loglikelihood. The advantages of the optimization techniques are demonstrated in numerical examples and in an application to Argo ocean temperature data. The new methods are more accurate and much faster than an optimization method that uses only function evaluations, especially when the covariance function has many parameters. This allows practitioners to fit nonstationary models to large spatial and spatial-temporal datasets.

stat.CO↗

arXiv2019

Smooth Density Spatial Quantile Regression

We derive the properties and demonstrate the desirability of a model-based method for estimating the spatially-varying effects of covariates on the quantile function. By modeling the quantile function as a combination of I-spline basis functions and Pareto tail distributions, we allow for flexible parametric modeling of the extremes while preserving non-parametric flexibility in the center of the distribution. We further establish that the model guarantees the desired degree of differentiability in the density function and enables the estimation of non-stationary covariance functions dependent on the predictors. We demonstrate through a simulation study that the proposed method produces more efficient estimates of the effects of predictors than other methods, particularly in distributions with heavy tails. To illustrate the utility of the model we apply it to measurements of benzene collected around an oil refinery to determine the effect of an emission source within the refinery on the distribution of the fence line measurements.

stat.ME↗

arXiv2019

Baseline Drift Estimation for Air Quality Data Using Quantile Trend Filtering

We address the problem of estimating smoothly varying baseline trends in time series data. This problem arises in a wide range of fields, including chemistry, macroeconomics, and medicine; however, our study is motivated by the analysis of data from low cost air quality sensors. Our methods extend the quantile trend filtering framework to enable the estimation of multiple quantile trends simultaneously while ensuring that the quantiles do not cross. To handle the computational challenge posed by very long time series, we propose a parallelizable alternating direction method of moments (ADMM) algorithm. The ADMM algorthim enables the estimation of trends in a piecewise manner, both reducing the computation time and extending the limits of the method to larger data sizes. We also address smoothing parameter selection and propose a modified criterion based on the extended Bayesian Information Criterion. Through simulation studies and our motivating application to low cost air quality sensor data, we demonstrate that our model provides better quantile trend estimates than existing methods and improves signal classification of low-cost air quality sensor output.

stat.ME↗

arXiv2018

Nonparametric Spectral Methods for Multivariate Spatial and Spatial-Temporal Data

We propose computationally efficient methods for estimating stationary multivariate spatial and spatial-temporal spectra from incomplete gridded data. The methods are iterative and rely on successive imputation of data and updating of model estimates. Imputations are done according to a periodic model on an expanded domain. The periodicity of the imputations is a key feature that reduces edge effects in the periodogram and is facilitated by efficient circulant embedding techniques. In addition, we describe efficient methods for decomposing the estimated cross spectral density function into a linear model of coregionalization plus a residual process. The methods are applied to two storm datasets, one of which is from Hurricane Florence, which struck the souteastern United States in September 2018. The application demonstrates how fitted models from different datasets can be compared, and how the methods are computationally feasible on datasets with more than 200,000 total observations.

stat.ME↗

arXiv2018

Non-Stationary Covariance Estimation using the Stochastic Score Approximation for Large Spatial Data

We introduce computational methods that allow for effective estimation of a flexible, parametric non-stationary spatial model when the field size is too large to compute the multivariate normal likelihood directly. In this method, the field is defined as a weighted spatially varying linear combination of a globally stationary process and locally stationary processes. Often in such a model, the difficulty in its practical use is in the definition of the boundaries for the local processes, and therefore we describe one such selection procedure that generally captures complex non-stationary relationships. We generalize the use of stochastic approximation to the score equations for data on a partial grid in this non-stationary case and provide tools for evaluating the approximate score in $O(n\log n)$ operations and $O(n)$ storage. We perform various simulations to explore the effectiveness and speed of the proposed methods and conclude by making inference on the accumulation behavior of arsenic applied to a sand grain.

stat.CO↗

arXiv2018

A class of multi-resolution approximations for large spatial datasets

Gaussian processes are popular and flexible models for spatial, temporal, and functional data, but they are computationally infeasible for large datasets. We discuss Gaussian-process approximations that use basis functions at multiple resolutions to achieve fast inference and that can (approximately) represent any spatial covariance structure. We consider two special cases of this multi-resolution-approximation framework, a taper version and a domain-partitioning (block) version. We describe theoretical properties and inference procedures, and study the computational complexity of the methods. Numerical comparisons and an application to satellite data are also provided.

stat.ME↗

arXiv2018

Multivariate Spatial-Temporal Variable Selection with Applications to Seasonal Tropical Cyclone Modeling

Tropical cyclone and sea surface temperature data have been used in several studies to forecast the total number of hurricanes in the Atlantic Basin. Sea surface temperature (SST) and latent heat flux (LHF) are correlated with tropical cyclone occurrences, but this correlation is known to vary with location and strength of the storm. The objective of this article is to identify features of SST and LHF that can explain the spatial-temporal variation of tropical cyclone counts, categorized by their strength. We develop a variable selection procedure for multivariate spatial-temporally varying coefficients, under a Poisson hurdle model (PHM) framework, which takes into account the zero-inflated nature of the counts. The method differs from current spatial-temporal variable selection techniques by offering a dynamic variable selection procedure, that shares information between responses, locations, time and levels in the PHM context. The model is used to study the association between SST and LHF and the number of tropical cyclones of different strengths in 400 locations in the Atlantic Basin over the period of 1950-2013. Results show that it is possible to estimate the number of tropical storms by season and region. Furthermore, the model delimits areas with a significant correlation between SST and LHF features and the occurrence and strength of TCs in the North Atlantic Basin.

stat.AP↗

arXiv2018

Permutation and Grouping Methods for Sharpening Gaussian Process Approximations

Vecchia's approximate likelihood for Gaussian process parameters depends on how the observations are ordered, which can be viewed as a deficiency because the exact likelihood is permutation-invariant. This article takes the alternative standpoint that the ordering of the observations can be tuned to sharpen the approximations. Advantageously chosen orderings can drastically improve the approximations, and in fact, completely random orderings often produce far more accurate approximations than default coordinate-based orderings do. In addition to the permutation results, automatic methods for grouping calculations of components of the approximation are introduced, having the result of simultaneously improving the quality of the approximation and reducing its computational burden. In common settings, reordering combined with grouping reduces Kullback-Leibler divergence from the target model by a factor of 80 and computation time by a factor of 2 compared to ungrouped approximations with default ordering. The claims are supported by theory and numerical results with comparisons to other approximations, including tapered covariances and stochastic partial differential equation approximations. Computational details are provided, including efficiently finding the orderings and ordered nearest neighbors, and profiling out linear mean parameters and using the approximations for prediction and conditional simulation. An application to space-time satellite data is presented.

stat.CO↗

arXiv2018

Compression and Conditional Emulation of Climate Model Output

Numerical climate model simulations run at high spatial and temporal resolutions generate massive quantities of data. As our computing capabilities continue to increase, storing all of the data is not sustainable, and thus it is important to develop methods for representing the full datasets by smaller compressed versions. We propose a statistical compression and decompression algorithm based on storing a set of summary statistics as well as a statistical model describing the conditional distribution of the full dataset given the summary statistics. The statistical model can be used to generate realizations representing the full dataset, along with characterizations of the uncertainties in the generated data. Thus, the methods are capable of both compression and conditional emulation of the climate models. Considerable attention is paid to accurately modeling the original dataset--one year of daily mean temperature data--particularly with regard to the inherent spatial nonstationarity in global fields, and to determining the statistics to be stored, so that the variation in the original data can be closely captured, while allowing for fast decompression and conditional emulation on modest computers.

stat.ME↗

arXiv2017

A Test for Isotropy on a Sphere using Spherical Harmonic Functions

Analysis of geostatistical data is often based on the assumption that the spatial random field is isotropic. This assumption, if erroneous, can adversely affect model predictions and statistical inference. Nowadays many applications consider data over the entire globe and hence it is necessary to check the assumption of isotropy on a sphere. In this paper, a test for spatial isotropy on a sphere is proposed. The data are first projected onto the set of spherical harmonic functions. Under isotropy, the spherical harmonic coefficients are uncorrelated whereas they are correlated if the underlying fields are not isotropic. This motivates a test based on the sample correlation matrix of the spherical harmonic coefficients. In particular, we use the largest eigenvalue of the sample correlation matrix as the test statistic. Extensive simulations are conducted to assess the Type I errors of the test under different scenarios. We show how temporal correlation affects the test and provide a method for handling temporal correlation. We also gauge the power of the test as we move away from isotropy. The method is applied to the near-surface air temperature data which is part of the HadCM3 model output. Although we do not expect global temperature fields to be isotropic, we propose several anisotropic models with increasing complexity, each of which has an isotropic process as model component and we apply the test to the isotropic component in a sequence of such models as a method of determining how well the models capture the anisotropy in the fields.

stat.ME↗

arXiv2016

An Evolutionary Spectrum Approach to Incorporate Large-scale Geographical Descriptors on Global Processes

We introduce a nonstationary spatio-temporal statistical model for gridded data on the sphere. The model specifies a computationally convenient covariance structure that depends on heterogeneous geography. Widely used statistical models on a spherical domain are nonstationary for different latitudes, but stationary at the same latitude (axial symmetry). This assumption has been acknowledged to be too restrictive for quantities such as surface temperature, whose statistical behavior is influenced by large scale geographical descriptors such as land and ocean. We propose an evolutionary spectrum approach that is able to account for different regimes across the Earth's geography, and results in a more general and flexible class of models that vastly outperforms axially symmetric models and captures longitudinal patterns that would otherwise be assumed constant. The model can be estimated with in a multi-step conditional likelihood approximation that preserves the nonstationary features while allowing for easily distributed computations: we show how the fit of a data sets larger than 20 million data can be performed in less than one day on a state-of-the-art workstation. Once the parameters are estimated, it is possible to instantaneously generate surrogate runs from a common laptop. Further, the resulting estimates from the statistical model can be regarded as a synthetic description (i.e. a compression) of the space-time characteristics of an entire initial condition ensemble. Compared to traditional algorithms aiming at compressing the bit-by-bit information on each climate model run, the proposed approach achieves vastly superior compression rates.

stat.AP↗

arXiv2013

Interpolation of nonstationary high frequency spatial-temporal temperature data

The Atmospheric Radiation Measurement program is a U.S. Department of Energy project that collects meteorological observations at several locations around the world in order to study how weather processes affect global climate change. As one of its initiatives, it operates a set of fixed but irregularly-spaced monitoring facilities in the Southern Great Plains region of the U.S. We describe methods for interpolating temperature records from these fixed facilities to locations at which no observations were made, which can be useful when values are required on a spatial grid. We interpolate by conditionally simulating from a fitted nonstationary Gaussian process model that accounts for the time-varying statistical characteristics of the temperatures, as well as the dependence on solar radiation. The model is fit by maximizing an approximate likelihood, and the conditional simulations result in well-calibrated confidence intervals for the predicted temperatures. We also describe methods for handling spatial-temporal jumps in the data to interpolate a slow-moving cold front.

stat.AP↗