arXiv subjects

Peter Hoff

Publications and source records attributed to Peter Hoff.

At least 19 recordsLinked to original sources

arXiv2026

Multiplicative Errors-in-Variables Models for Hyperspectral Unmixing

Estimating endmember spectra and their corresponding abundances from hyperspectral images is a fundamental inverse problem in remote sensing. The standard linear mixing model relies on additive homoscedastic errors, which misspecifies the mean-variance relationship inherent to optical measurements for which the noise intensity might be proportional to the signal magnitude. This leads to confidence intervals with poor coverage. To address these limitations, we propose a hierarchical Bayesian multiplicative Errors-in-Variables (EIV) model. Motivated by the physics of light propagation, our formulation captures signal-dependent noise through a multivariate log-normal specification that naturally accommodates dependence across spectral bands. The EIV framework treats endmember signatures as random and allows for class-specific variance scaling, yielding a flexible and physically grounded data-generating process. We establish that the MLE of the abundance vector under the multiplicative model has a constant asymptotic multivariate coefficient of variation, implying that well-calibrated confidence intervals should scale proportionally with signal magnitude. The additive model, by contrast, produces intervals of constant width regardless of signal magnitude, leading to overcoverage at low abundance and undercoverage at high abundance when the true noise is multiplicative. Practical implementation and inference for the full hierarchical model is obtained from posterior distributions over the model parameters. Experiments on several real and simulated datasets demonstrate that confidence intervals derived from the proposed model achieve improved coverage across abundance levels compared to those from a standard additive model, with widths that scale proportionally with signal magnitude, while achieving comparable or superior signal reconstruction error.

stat.ME↗

arXiv2026

Extended rank regression for all ordinal data

The accuracy of inference from a regression model depends largely on how well the model represents the relationship between the mean and variance of the outcomes. As this relationship is rarely of direct interest, it is natural to treat it as a nuisance parameter, rather than attempt to estimate it. We take this approach in the context of a monotonically transformed linear regression model using a pseudo-likelihood based on an extended notion of ranks. This approach can accommodate a wide range of mean-variance relationships and any ordinal data type, including continuous and discrete ordered data, and requires no estimation or prior specification of the transformation, or decision to treat an outcome as continuous or discrete. We show that the extended rank likelihood incurs no asymptotic information loss at the two extremes of continuous and binary data, and that rank-based prediction intervals can obtain approximate coverage control conditional on the features. Bayesian parameter estimates and prediction intervals are available via a simple Gibbs sampling algorithm. For settings where the model is in doubt, conformal calibration of the Bayesian predictive distribution provides intervals with guaranteed marginal frequentist coverage.

stat.ME↗

arXiv2025

Selective and marginal selective inference for exceptional groups

Statistical analyses of multipopulation studies often use the data to select a particular population as the target of inference. For example, a confidence interval may be constructed for a population only in the event that its sample mean is larger than that of the other populations. We show that for the normal means model, confidence interval procedures that maintain strict coverage control conditional on such a selection event will have infinite expected width. For applications where such selective coverage control is of interest, this result motivates the development of procedures with finite expected width and approximate selective coverage control over a range of plausible parameter values. To this end, we develop selection-adjusted empirical Bayes confidence procedures that use information from the data to approximate an oracle confidence procedure that has exact selective coverage control and finite expected width. In numerical comparisons of the oracle and empirical Bayes procedures to procedures that only guarantee selective coverage control marginally over selection events, we find that improved selective coverage control comes at the cost of increased expected interval width.

math.ST↗

arXiv2025

Prior distributions for structured semi-orthogonal matrices

Statistical models for multivariate data often include a semi-orthogonal matrix parameter. In many applications, there is reason to expect that the semi-orthogonal matrix parameter satisfies a structural assumption such as sparsity or smoothness. From a Bayesian perspective, these structural assumptions should be incorporated into an analysis through the prior distribution. In this work, we introduce a general approach to constructing prior distributions for structured semi-orthogonal matrices that leads to tractable posterior inference via parameter-expanded Markov chain Monte Carlo. We draw on recent results from random matrix theory to establish a theoretical basis for the proposed approach. We then introduce specific prior distributions for incorporating sparsity or smoothness and illustrate their use through applications to biological and oceanographic data.

stat.ME↗

arXiv2024

Evaluation of the linear mixing model in fluorescence spectroscopy

Analyses of spectral data often assume a linear mixing hypothesis, which states that the spectrum of a mixed substance is approximately the mixture of the individual spectra of its constituent parts. We evaluate this hypothesis in the context of dissolved organic matter (DOM) fluorescence spectroscopy for endmember abundance recovery from mixtures of three different DOM endmembers. We quantify two key sources of experimental variation, and statistically evaluate the linear mixing hypotheses in the context of this variation. We find that there is not strong statistical evidence against this hypothesis for high-fluorescence readings, and that true abundances of high-fluorescence endmembers are accurately recovered from the excitation-emission fluorescence spectra of mixed samples using linear methods. However, abundances of a low-fluorescence endmember are less well-estimated, in that the abundance coefficient estimates exhibit a high degree of variability across replicate experiments.

stat.AP↗

arXiv2023

Linear Source Apportionment using Generalized Least Squares

Motivated by applications to water quality monitoring using fluorescence spectroscopy, we develop the source apportionment model for high dimensional profiles of dissolved organic matter (DOM). We describe simple methods to estimate the parameters of a linear source apportionment model, and show how the estimates are related to those of ordinary and generalized least squares. Using this least squares framework, we analyze the variability of the estimates, and we propose predictors for missing elements of a DOM profile. We demonstrate the practical utility of our results on fluorescence spectroscopy data collected from the Neuse River in North Carolina.

stat.AP↗

arXiv2023

Information Geometry and Asymptotics for Kronecker Covariances

We explore the information geometry and asymptotic behaviour of estimators for Kronecker-structured covariances, in both growing-$n$ and growing-$p$ scenarios, with a focus towards examining the quadratic form or partial trace estimator proposed by Linton and Tang. It is shown that the partial trace estimator is asymptotically inefficient An explanation for this inefficiency is that the partial trace estimator does not scale sub-blocks of the sample covariance matrix optimally. To correct for this, an asymptotically efficient, rescaled partial trace estimator is proposed. Motivated by this rescaling, we introduce an orthogonal parameterization for the set of Kronecker covariances. High-dimensional consistency results using the partial trace estimator are obtained that demonstrate a blessing of dimensionality. In settings where an array has at least order three, it is shown that as the array dimensions jointly increase, it is possible to consistently estimate the Kronecker covariance matrix, even when the sample size is one.

math.ST↗

arXiv2022

Core Shrinkage Covariance Estimation for Matrix-variate Data

A separable covariance model for a random matrix provides a parsimonious description of the covariances among the rows and among the columns of the matrix, and permits likelihood-based inference with a very small sample size. However, in many applications the assumption of exact separability is unlikely to be met, and data analysis with a separable model may overlook or misrepresent important dependence patterns in the data. In this article, we propose a compromise between separable and unstructured covariance estimation. We show how the set of covariance matrices may be uniquely parametrized in terms of the set of separable covariance matrices and a complementary set of "core" covariance matrices, where the core of a separable covariance matrix is the identity matrix. This parametrization defines a Kronecker-core decomposition of a covariance matrix. By shrinking the core of the sample covariance matrix with an empirical Bayes procedure, we obtain an estimator that can adapt to the degree of separability of the population covariance matrix.

stat.ME↗

arXiv2022

Tests of Linear Hypotheses using Indirect Information

In multigroup data settings with small within-group sample sizes, standard $F$-tests of group-specific linear hypotheses can have low power, particularly if the within-group sample sizes are not large relative to the number of explanatory variables. To remedy this situation, in this article we derive alternative test statistics based on information-sharing across groups. Each group-specific test has potentially much larger power than the standard $F$-test, while still exactly maintaining a target type I error rate if the hypothesis for the group is true. The proposed test for a given group uses a statistic that has optimal marginal power under a prior distribution derived from the data of the other groups. This statistic approaches the usual $F$-statistic as the prior distribution becomes more diffuse, but approaches a limiting "cone" test statistic as the prior distribution becomes extremely concentrated. We compare the power and $p$-values of the cone test to that of the $F$-test in some high-dimensional asymptotic scenarios. An analysis of educational outcome data is provided, demonstrating empirically that the proposed test is more powerful than the $F$-test.

stat.ME↗

arXiv2022

Coverage Properties of Empirical Bayes Intervals

This note is an invited discussion of the article "Confidence Intervals for Nonparametric Empirical Bayes Analysis" by Ignatiadis and Wager. In this discussion, I review some goals of empirical Bayes data analysis and the contribution of Ignatiadis and Wager. Differences between across-group inference and group-specific inference are discussed. Standard empirical Bayes interval procedures focus on controlling the across-group average coverage rate. However, if group-specific inferences are of primary interest, confidence intervals with group-specific coverage control may be preferable.

stat.ME↗

arXiv2021

Bayes-optimal prediction with frequentist coverage control

This article illustrates how indirect or prior information can be optimally used to construct a prediction region that maintains a target frequentist coverage rate. If the indirect information is accurate, the volume of the prediction region is lower on average than that of other regions with the same coverage rate. Even if the indirect information is inaccurate, the resulting region still maintains the target coverage rate. Such a prediction region can be constructed for models that have a complete sufficient statistic, which includes many widely-used parametric and nonparametric models. Particular examples include a Bayes-optimal conformal prediction procedure that maintains a constant coverage rate across distributions in a nonparametric model, as well as a prediction procedure for the normal linear regression model that can utilize a regularizing prior distribution, yet maintain a frequentist coverage rate that is constant as a function of the model parameters and explanatory variables. No results in this article rely on asymptotic approximations.

math.ST↗

arXiv2021

Equivariant Estimation of Fr\'echet Means

The Fr\'echet mean generalizes the concept of a mean to a metric space setting. In this work we consider equivariant estimation of Fr\'echet means for parametric models on metric spaces that are Riemannian manifolds. The geometry and symmetry of such a space is encoded by its isometry group. Estimators that are equivariant under the isometry group take into account the symmetry of the metric space. For some models there exists an optimal equivariant estimator, which necessarily will perform as well or better than other common equivariant estimators, such as the maximum likelihood estimator or the sample Fr\'echet mean. We derive the general form of this minimum risk equivariant estimator and in a few cases provide explicit expressions for it. In other models the isometry group is not large enough relative to the parametric family of distributions for there to exist a minimum risk equivariant estimator. In such cases, we introduce an adaptive equivariant estimator that uses the data to select a submodel for which there is an MRE. Simulations results show that the adaptive equivariant estimator performs favorably relative to alternative estimators.

math.ST↗

arXiv2020

The Stein Effect for Frechet Means

The Frechet mean is a useful description of location for a probability distribution on a metric space that is not necessarily a vector space. This article considers simultaneous estimation of multiple Frechet means from a decision-theoretic perspective, and in particular, the extent to which the unbiased estimator of a Frechet mean can be dominated by a generalization of the James-Stein shrinkage estimator. It is shown that if the metric space satisfies a non-positive curvature condition, then this generalized James-Stein estimator asymptotically dominates the unbiased estimator as the dimension of the space grows. These results hold for a large class of distributions on a variety of spaces - including Hilbert spaces - and therefore partially extend known results on the applicability of the James-Stein estimator to non-normal distributions on Euclidean spaces. Simulation studies on metric trees and symmetric-positive-definite matrices are presented, numerically demonstrating the efficacy of this generalized James-Stein estimator.

math.ST↗

arXiv2020

Existence and Uniqueness of the Kronecker Covariance MLE

In matrix-valued datasets the sampled matrices often exhibit correlations among both their rows and their columns. A useful and parsimonious model of such dependence is the matrix normal model, in which the covariances among the elements of a random matrix are parameterized in terms of the Kronecker product of two covariance matrices, one representing row covariances and one representing column covariance. An appealing feature of such a matrix normal model is that the Kronecker covariance structure allows for standard likelihood inference even when only a very small number of data matrices is available. For instance, in some cases a likelihood ratio test of dependence may be performed with a sample size of one. However, more generally the sample size required to ensure boundedness of the matrix normal likelihood or the existence of a unique maximizer depends in a complicated way on the matrix dimensions. This motivates the study of how large a sample size is needed to ensure that maximum likelihood estimators exist, and exist uniquely with probability one. Our main result gives precise sample size thresholds in the paradigm where the number of rows and the number of columns of the data matrices differ by at most a factor of two. Our proof uses invariance properties that allow us to consider data matrices in canonical form, as obtained from the Kronecker canonical form for matrix pencils.

math.ST↗

arXiv2018

Exact adaptive confidence intervals for small areas

In the analysis of survey data it is of interest to estimate and quantify uncertainty about means or totals for each of several non-overlapping subpopulations, or areas. When the sample size for a given area is small, standard confidence intervals based on data only from that area can be unacceptably wide. In order to reduce interval width, practitioners often utilize multilevel models in order to borrow information across areas, resulting in intervals centered around shrinkage estimators. However, such intervals only have the nominal coverage rate on average across areas under the assumed model for across-area heterogeneity. The coverage rate for a given area depends on the actual value of the area mean, and can be nearly zero for areas with means that are far from the across-group average. As such, the use of uncertainty intervals centered around shrinkage estimators are inappropriate when area-specific coverage rates are desired. In this article, we propose an alternative confidence interval procedure for area means and totals under normally distributed sampling errors. This procedure not only has constant $1-\alpha$ frequentist coverage for all values of the target quantity, but also uses auxiliary information to borrow information across areas. Because of this, the corresponding intervals have shorter expected lengths than standard confidence intervals centered on the unbiased direct estimator. Importantly, the coverage of the procedure does not depend on the assumed model for across-area heterogeneity. Rather, improvements to the model for across-area heterogeneity result in reduced expected interval width.

stat.ME↗

arXiv2016

Shared Subspace Models for Multi-Group Covariance Estimation

We develop a model-based method for evaluating heterogeneity among several p x p covariance matrices in the large p, small n setting. This is done by assuming a spiked covariance model for each group and sharing information about the space spanned by the group-level eigenvectors. We use an empirical Bayes method to identify a low-dimensional subspace which explains variation across all groups and use an MCMC algorithm to estimate the posterior uncertainty of eigenvectors and eigenvalues on this subspace. The implementation and utility of our model is illustrated with analyses of high-dimensional multivariate gene expression.

stat.ME↗

arXiv2015

Adaptive Higher-order Spectral Estimators

Many applications involve estimation of a signal matrix from a noisy data matrix. In such cases, it has been observed that estimators that shrink or truncate the singular values of the data matrix perform well when the signal matrix has approximately low rank. In this article, we generalize this approach to the estimation of a tensor of parameters from noisy tensor data. We develop new classes of estimators that shrink or threshold the mode-specific singular values from the higher-order singular value decomposition. These classes of estimators are indexed by tuning parameters, which we adaptively choose from the data by minimizing Stein's unbiased risk estimate. In particular, this procedure provides a way to estimate the multilinear rank of the underlying signal tensor. Using simulation studies under a variety of conditions, we show that our estimators perform well when the mean tensor has approximately low multilinear rank, and perform competitively when the signal tensor does not have approximately low multilinear rank. We illustrate the use of these methods in an application to multivariate relational data.

stat.ME↗

arXiv2014

Equivariant minimax dominators of the MLE in the array normal model

Inference about dependencies in a multiway data array can be made using the array normal model, which corresponds to the class of multivariate normal distributions with separable covariance matrices. Maximum likelihood and Bayesian methods for inference in the array normal model have appeared in the literature, but there have not been any results concerning the optimality properties of such estimators. In this article, we obtain results for the array normal model that are analogous to some classical results concerning covariance estimation for the multivariate normal model. We show that under a lower triangular product group, a uniformly minimum risk equivariant estimator (UMREE) can be obtained via a generalized Bayes procedure. Although this UMREE is minimax and dominates the MLE, it can be improved upon via an orthogonally equivariant modification. Numerical comparisons of the risks of these estimators show that the equivariant estimators can have substantially lower risks than the MLE.

math.ST↗