arXiv subjects

David Degras

Publications and source records attributed to David Degras.

10 recordsLinked to original sources

arXiv2021

Markov-Switching State-Space Models with Applications to Neuroimaging

State-space models (SSM) with Markov switching offer a powerful framework for detecting multiple regimes in time series, analyzing mutual dependence and dynamics within regimes, and asserting transitions between regimes. These models however present considerable computational challenges due to the exponential number of possible regime sequences to account for. In addition, high dimensionality of time series can hinder likelihood-based inference. This paper proposes novel statistical methods for Markov-switching SSMs using maximum likelihood estimation, Expectation-Maximization (EM), and parametric bootstrap. We develop solutions for initializing the EM algorithm, accelerating convergence, and conducting inference that are ideally suited to massive spatio-temporal data such as brain signals. We evaluate these methods in simulations and present applications to EEG studies of epilepsy and of motor imagery. All proposed methods are implemented in a MATLAB toolbox available at https://github.com/ddegras/switch-ssm.

stat.ME↗

arXiv2021

Scalable Feature Matching Across Large Data Collections

This paper is concerned with matching feature vectors in a one-to-one fashion across large collections of datasets. Formulating this task as a multidimensional assignment problem with decomposable costs (MDADC), we develop extremely fast algorithms with time complexity linear in the number $n$ of datasets and space complexity a small fraction of the data size. These remarkable properties hinge on using the squared Euclidean distance as dissimilarity function, which can reduce ${n \choose 2}$ matching problems between pairs of datasets to $n$ problems and enable calculating assignment costs on the fly. To our knowledge, no other method applicable to the MDADC possesses these linear scaling and low-storage properties necessary to large-scale applications. In numerical experiments, the novel algorithms outperform competing methods and show excellent computational and optimization performances. An application of feature matching to a large neuroimaging database is presented. The algorithms of this paper are implemented in the R package matchFeat available at https://github.com/ddegras/matchFeat.

stat.CO↗

arXiv2019

Sparse Group Fused Lasso for Model Segmentation

This article introduces the sparse group fused lasso (SGFL) as a statistical framework for segmenting sparse regression models with multivariate time series. To compute solutions of the SGFL, a nonsmooth and nonseparable convex program, we develop a hybrid optimization method that is fast, requires no tuning parameter selection, and is guaranteed to converge to a global minimizer. In numerical experiments, the hybrid method compares favorably to state-of-the-art techniques with respect to computation time and numerical accuracy; benefits are particularly substantial in high dimension. The method's statistical performance is satisfactory in recovering nonzero regression coefficients and excellent in change point detection. An application to air quality data is presented. The hybrid method is implemented in the R package sparseGFL available on the author's Github page.

stat.CO↗

arXiv2015

Online Principal Component Analysis in High Dimension: Which Algorithm to Choose?

In the current context of data explosion, online techniques that do not require storing all data in memory are indispensable to routinely perform tasks like principal component analysis (PCA). Recursive algorithms that update the PCA with each new observation have been studied in various fields of research and found wide applications in industrial monitoring, computer vision, astronomy, and latent semantic indexing, among others. This work provides guidance for selecting an online PCA algorithm in practice. We present the main approaches to online PCA, namely, perturbation techniques, incremental methods, and stochastic optimization, and compare their statistical accuracy, computation time, and memory requirements using artificial and real data. Extensions to missing data and to functional data are discussed. All studied algorithms are available in the R package onlinePCA on CRAN.

stat.ML↗

arXiv2014

A hierarchical model for simultaneous detection and estimation in multi-subject fMRI Studies

In this paper we introduce a new hierarchical model for the simultaneous detection of brain activation and estimation of the shape of the hemodynamic response in multi-subject fMRI studies. The proposed approach circumvents a major stumbling block in standard multi-subject fMRI data analysis, in that it both allows the shape of the hemodynamic response function to vary across region and subjects, while still providing a straightforward way to estimate population-level activation. An efficient estimation algorithm is presented, as is an inferential framework that not only allows for tests of activation, but also for tests for deviations from some canonical shape. The model is validated through simulations and application to a multi-subject fMRI study of thermal pain.

stat.AP↗

arXiv2013

Confidence bands for Horvitz-Thompson estimators using sampled noisy functional data

When collections of functional data are too large to be exhaustively observed, survey sampling techniques provide an effective way to estimate global quantities such as the population mean function. Assuming functional data are collected from a finite population according to a probabilistic sampling scheme, with the measurements being discrete in time and noisy, we propose to first smooth the sampled trajectories with local polynomials and then estimate the mean function with a Horvitz-Thompson estimator. Under mild conditions on the population size, observation times, regularity of the trajectories, sampling scheme, and smoothing bandwidth, we prove a Central Limit theorem in the space of continuous functions. We also establish the uniform consistency of a covariance function estimator and apply the former results to build confidence bands for the mean function. The bands attain nominal coverage and are obtained through Gaussian process simulations conditional on the estimated covariance function. To select the bandwidth, we propose a cross-validation method that accounts for the sampling weights. A simulation study assesses the performance of our approach and highlights the influence of the sampling scheme and bandwidth choice.

math.ST↗

arXiv2013

Rotation Sampling for Functional Data

This paper addresses the survey estimation of a population mean in continuous time. For this purpose we extend the rotation sampling method to functional data. In contrast to conventional rotation designs that select the sample before the survey, our approach randomizes each sample replacement and thus allows for adaptive sampling. Using Markov chain theory, we evaluate the covariance structure and the integrated squared error [ISE] of the related Horvitz-Thompson estimator. Our sampling designs decrease the mean ISE by suitably reallocating the sample across population strata during replacements. They also reduce the variance of the ISE by increasing the frequency or the intensity of replacements. To investigate the benefits of using both current and past measurements in the estimation, we develop a new composite estimator. In an application to electricity usage data, our rotation method outperforms fixed panels and conventional rotation samples. Because of the weak temporal dependence of the data, the composite estimator only slightly improves upon the Horvitz-Thompson estimator.

stat.ME↗

arXiv2011

Local Polynomial Regression Based on Functional Data

Suppose that $n$ statistical units are observed, each following the model $Y(x_j)=m(x_j)+ ε(x_j),\, j=1,...,N,$ where $m$ is a regression function, $0 \leq x_1 <...<x_N \leq 1$ are observation times spaced according to a sampling density $f$, and $ε$ is a continuous-time error process having mean zero and regular covariance function. Considering the local polynomial estimation of $m$ and its derivatives, we derive asymptotic expressions for the bias and variance as $n,N\to\infty$. Such results are particularly relevant in the context of functional data where essential information is contained in the derivatives. Based on these results, we deduce optimal sampling densities, optimal bandwidths and asymptotic normality of the estimator. Simulations are conducted in order to compare the performances of local polynomial estimators based on exact optimal bandwidths, asymptotic optimal bandwidths, and cross-validated bandwidths.

math.ST↗

arXiv2011

Testing for Parallelism Between Trends in Multiple Time Series

This paper considers the inference of trends in multiple, nonstationary time series. To test whether trends are parallel to each other, we use a parallelism index based on the L2-distances between nonparametric trend estimators and their average. A central limit theorem is obtained for the test statistic and the test's consistency is established. We propose a simulation-based approximation to the distribution of the test statistic, which significantly improves upon the normal approximation. The test is also applied to devise a clustering algorithm. Finally, the finite-sample properties of the test are assessed through simulations and the test methodology is illustrated with time series from Motorola cell phone activity in the United States.

stat.ME↗

arXiv2011

Nonparametric estimation of a trend based upon sampled continuous processes

Let X be a second order random process indexed by a compact interval [0,T]. Assume that n independent realizations of X are observed on a fixed grid of p time points. Under mild regularity assumptions on the sample paths of X, we show the asymptotic normality of suitable nonparametric estimators of the trend function mu = EX in the space C([0,T]) as n, p go to infinity and, using Gaussian process theory, we derive approximate simultaneous confidence bands for mu.

math.ST↗