arXiv subjects

David S. Matteson

Publications and source records attributed to David S. Matteson.

At least 55 records · Page 3Linked to original sources

arXiv2020

High Dimensional Forecasting via Interpretable Vector Autoregression

Vector autoregression (VAR) is a fundamental tool for modeling multivariate time series. However, as the number of component series is increased, the VAR model becomes overparameterized. Several authors have addressed this issue by incorporating regularized approaches, such as the lasso in VAR estimation. Traditional approaches address overparameterization by selecting a low lag order, based on the assumption of short range dependence, assuming that a universal lag order applies to all components. Such an approach constrains the relationship between the components and impedes forecast performance. The lasso-based approaches work much better in high-dimensional situations but do not incorporate the notion of lag order selection. We propose a new class of hierarchical lag structures (HLag) that embed the notion of lag selection into a convex regularizer. The key modeling tool is a group lasso with nested groups which guarantees that the sparsity pattern of lag coefficients honors the VAR's ordered structure. The HLag framework offers three structures, which allow for varying levels of flexibility. A simulation study demonstrates improved performance in forecasting and lag order selection over previous approaches, and a macroeconomic application further highlights forecasting improvements as well as HLag's convenient, interpretable output.

stat.ME↗

arXiv2020

Factor Analysis of Mixed Data for Anomaly Detection

Anomaly detection aims to identify observations that deviate from the typical pattern of data. Anomalous observations may correspond to financial fraud, health risks, or incorrectly measured data in practice. We show detecting anomalies in high-dimensional mixed data is enhanced through first embedding the data then assessing an anomaly scoring scheme. We focus on unsupervised detection and the continuous and categorical (mixed) variable case. We propose a kurtosis-weighted Factor Analysis of Mixed Data for anomaly detection, FAMDAD, to obtain a continuous embedding for anomaly scoring. We illustrate that anomalies are highly separable in the first and last few ordered dimensions of this space, and test various anomaly scoring experiments within this subspace. Results are illustrated for both simulated and real datasets, and the proposed approach (FAMDAD) is highly accurate for high-dimensional mixed data throughout these diverse scenarios.

stat.ML↗

arXiv2019

Cell Line Classification Using Electric Cell-substrate Impedance Sensing (ECIS)

We consider cell line classification using multivariate time series data obtained from electric cell-substrate impedance sensing (ECIS) technology. The ECIS device, which monitors the attachment and spreading of mammalian cells in real time through the collection of electrical impedance data, has historically been used to study one cell line at a time. However, we show that if applied to data from multiple cell lines, ECIS can be used to classify unknown or potentially mislabeled cells, which may help to mitigate the current crisis of reproducibility in the biological literature. We assess a range of approaches to this new problem, testing different classification methods and deriving a dictionary of 29 features to characterize ECIS data. Our analysis also makes use of simultaneous multi-frequency ECIS data, where previous studies have focused on only one frequency. In classification tests on fifteen mammalian cell lines, we obtain very high out-of-sample accuracy. These preliminary findings provide a baseline for future large-scale studies in this field.

q-bio.QM↗

arXiv2018

Independent Component Analysis via Energy-based and Kernel-based Mutual Dependence Measures

We apply both distance-based (Jin and Matteson, 2017) and kernel-based (Pfister et al., 2016) mutual dependence measures to independent component analysis (ICA), and generalize dCovICA (Matteson and Tsay, 2017) to MDMICA, minimizing empirical dependence measures as an objective function in both deflation and parallel manners. Solving this minimization problem, we introduce Latin hypercube sampling (LHS) (McKay et al., 2000), and a global optimization method, Bayesian optimization (BO) (Mockus, 1994) to improve the initialization of the Newton-type local optimization method. The performance of MDMICA is evaluated in various simulation studies and an image data example. When the ICA model is correct, MDMICA achieves competitive results compared to existing approaches. When the ICA model is misspecified, the estimated independent components are less mutually dependent than the observed components using MDMICA, while they are prone to be even more mutually dependent than the observed components using other approaches.

stat.ME↗

arXiv2018

Testing for Conditional Mean Independence with Covariates through Martingale Difference Divergence

As a crucial problem in statistics is to decide whether additional variables are needed in a regression model. We propose a new multivariate test to investigate the conditional mean independence of Y given X conditioning on some known effect Z, i.e., E(Y|X, Z) = E(Y|Z). Assuming that E(Y|Z) and Z are linearly related, we reformulate an equivalent notion of conditional mean independence through transformation, which is approximated in practice. We apply the martingale difference divergence (Shao and Zhang, 2014) to measure conditional mean dependence, and show that the estimation error from approximation is negligible, as it has no impact on the asymptotic distribution of the test statistic under some regularity assumptions. The implementation of our test is demonstrated by both simulations and a financial data example.

math.ST↗

arXiv2018

Generalizing Distance Covariance to Measure and Test Multivariate Mutual Dependence

We propose three measures of mutual dependence between multiple random vectors. All the measures are zero if and only if the random vectors are mutually independent. The first measure generalizes distance covariance from pairwise dependence to mutual dependence, while the other two measures are sums of squared distance covariance. All the measures share similar properties and asymptotic distributions to distance covariance, and capture non-linear and non-monotone mutual dependence between the random vectors. Inspired by complete and incomplete V-statistics, we define the empirical measures and simplified empirical measures as a trade-off between the complexity and power when testing mutual independence. Implementation of the tests is demonstrated by both simulation results and real data examples.

math.ST↗

arXiv2018

Dynamic Shrinkage Processes

We propose a novel class of dynamic shrinkage processes for Bayesian time series and regression analysis. Building upon a global-local framework of prior construction, in which continuous scale mixtures of Gaussian distributions are employed for both desirable shrinkage properties and computational tractability, we model dependence among the local scale parameters. The resulting processes inherit the desirable shrinkage behavior of popular global-local priors, such as the horseshoe prior, but provide additional localized adaptivity, which is important for modeling time series data or regression functions with local features. We construct a computationally efficient Gibbs sampling algorithm based on a Pólya-Gamma scale mixture representation of the proposed process. Using dynamic shrinkage processes, we develop a Bayesian trend filtering model that produces more accurate estimates and tighter posterior credible intervals than competing methods, and apply the model for irregular curve-fitting of minute-by-minute Twitter CPU usage data. In addition, we develop an adaptive time-varying parameter regression model to assess the efficacy of the Fama-French five-factor asset pricing model with momentum added as a sixth factor. Our dynamic analysis of manufacturing and healthcare industry data shows that with the exception of the market risk, no other risk factors are significant except for brief periods.

stat.ME↗

arXiv2017

Optimization and Testing in Linear Non-Gaussian Component Analysis

Independent component analysis (ICA) decomposes multivariate data into mutually independent components (ICs). The ICA model is subject to a constraint that at most one of these components is Gaussian, which is required for model identifiability. Linear non-Gaussian component analysis (LNGCA) generalizes the ICA model to a linear latent factor model with any number of both non-Gaussian components (signals) and Gaussian components (noise), where observations are linear combinations of independent components. Although the individual Gaussian components are not identifiable, the Gaussian subspace is identifiable. We introduce an estimator along with its optimization approach in which non-Gaussian and Gaussian components are estimated simultaneously, maximizing the discrepancy of each non-Gaussian component from Gaussianity while minimizing the discrepancy of each Gaussian component from Gaussianity. When the number of non-Gaussian components is unknown, we develop a statistical test to determine it based on resampling and the discrepancy of estimated components. Through a variety of simulation studies, we demonstrate the improvements of our estimator over competing estimators, and we illustrate the effectiveness of the test to determine the number of non-Gaussian components. Further, we apply our method to real data examples and demonstrate its practical value.

stat.ME↗

arXiv2017

Interpretable Vector AutoRegressions with Exogenous Time Series

The Vector AutoRegressive (VAR) model is fundamental to the study of multivariate time series. Although VAR models are intensively investigated by many researchers, practitioners often show more interest in analyzing VARX models that incorporate the impact of unmodeled exogenous variables (X) into the VAR. However, since the parameter space grows quadratically with the number of time series, estimation quickly becomes challenging. While several proposals have been made to sparsely estimate large VAR models, the estimation of large VARX models is under-explored. Moreover, typically these sparse proposals involve a lasso-type penalty and do not incorporate lag selection into the estimation procedure. As a consequence, the resulting models may be difficult to interpret. In this paper, we propose a lag-based hierarchically sparse estimator, called "HVARX", for large VARX models. We illustrate the usefulness of HVARX on a cross-category management marketing application. Our results show how it provides a highly interpretable model, and improves out-of-sample forecast accuracy compared to a lasso-type approach.

stat.ML↗

arXiv2017

Linear Non-Gaussian Component Analysis via Maximum Likelihood

Independent component analysis (ICA) is popular in many applications, including cognitive neuroscience and signal processing. Due to computational constraints, principal component analysis is used for dimension reduction prior to ICA (PCA+ICA), which could remove important information. The problem is that interesting independent components (ICs) could be mixed in several principal components that are discarded and then these ICs cannot be recovered. We formulate a linear non-Gaussian component model with Gaussian noise components. To estimate this model, we propose likelihood component analysis (LCA), in which dimension reduction and latent variable estimation are achieved simultaneously. Our method orders components by their marginal likelihood rather than ordering components by variance as in PCA. We present a parametric LCA using the logistic density and a semi-parametric LCA using tilted Gaussians with cubic B-splines. Our algorithm is scalable to datasets common in applications (e.g., hundreds of thousands of observations across hundreds of variables with dozens of latent components). In simulations, latent components are recovered that are discarded by PCA+ICA methods. We apply our method to multivariate data and demonstrate that LCA is a useful data visualization and dimension reduction tool that reveals features not apparent from PCA or PCA+ICA. We also apply our method to an fMRI experiment from the Human Connectome Project and identify artifacts missed by PCA+ICA. We present theoretical results on identifiability of the linear non-Gaussian component model and consistency of LCA.

stat.ME↗

arXiv2016

Mixed Data and Classification of Transit Stops

An analysis of the characteristics and behavior of individual bus stops can reveal clusters of similar stops, which can be of use in making routing and scheduling decisions, as well as determining what facilities to provide at each stop. This paper provides an exploratory analysis, including several possible clustering results, of a dataset provided by the Regional Transit Service of Rochester, NY. The dataset describes ridership on public buses, recording the time, location, and number of entering and exiting passengers each time a bus stops. A description of the overall behavior of bus ridership is followed by a stop-level analysis. We compare multiple measures of stop similarity, based on location, route information, and ridership volume over time.

stat.AP↗

arXiv2016

Functional Autoregression for Sparsely Sampled Data

We develop a hierarchical Gaussian process model for forecasting and inference of functional time series data. Unlike existing methods, our approach is especially suited for sparsely or irregularly sampled curves and for curves sampled with non-negligible measurement error. The latent process is dynamically modeled as a functional autoregression (FAR) with Gaussian process innovations. We propose a fully nonparametric dynamic functional factor model for the dynamic innovation process, with broader applicability and improved computational efficiency over standard Gaussian process models. We prove finite-sample forecasting and interpolation optimality properties of the proposed model, which remain valid with the Gaussian assumption relaxed. An efficient Gibbs sampling algorithm is developed for estimation, inference, and forecasting, with extensions for FAR(p) models with model averaging over the lag p. Extensive simulations demonstrate substantial improvements in forecasting performance and recovery of the autoregressive surface over competing methods, especially under sparse designs. We apply the proposed methods to forecast nominal and real yield curves using daily U.S. data. Real yields are observed more sparsely than nominal yields, yet the proposed methods are highly competitive in both settings.

stat.ME↗

arXiv2015

Band Depth Clustering for Nonstationary Time Series and Wind Speed Behavior

We explore the behavior of wind speed over time, using the Eastern Wind Dataset published by the National Renewable Energy Laboratory. This dataset gives wind speeds over three years at hundreds of potential wind farm sites. Wind speed analysis is necessary to the integration of wind energy into the power grid; short-term variability in wind speed affects decisions about usage of other power sources, so that the shape of the wind speed curve becomes as important as the overall level. To assess differences in intra-day time series, we propose a functional distance measure, the band distance, which extends the band depth of Lopez-Pintado and Romo (2009). This measure emphasizes the shape of time series or functional observations relative to other members of a dataset, and allows clustering of observations without reliance on pointwise Euclidean distance. To emphasize short-term variability, we examine the short-time Fourier transform of the nonstationary speed time series; we can also adjust for seasonal effects, and use these standardizations as input for the band distance. We show that these approaches to characterizing the data go beyond mean-dependent standard clustering methods, such as k-means, to provide more shape-influenced cluster representatives useful for power grid decisions.

stat.AP↗

arXiv2015

A Bayesian Multivariate Functional Dynamic Linear Model

We present a Bayesian approach for modeling multivariate, dependent functional data. To account for the three dominant structural features in the data--functional, time dependent, and multivariate components--we extend hierarchical dynamic linear models for multivariate time series to the functional data setting. We also develop Bayesian spline theory in a more general constrained optimization framework. The proposed methods identify a time-invariant functional basis for the functional observations, which is smooth and interpretable, and can be made common across multivariate observations for additional information sharing. The Bayesian framework permits joint estimation of the model parameters, provides exact inference (up to MCMC error) on specific parameters, and allows generalized dependence structures. Sampling from the posterior distribution is accomplished with an efficient Gibbs sampling algorithm. We illustrate the proposed framework with two applications: (1) multi-economy yield curve data from the recent global recession, and (2) local field potential brain signals in rats, for which we develop a multivariate functional time series approach for multivariate time-frequency analysis. Supplementary materials, including R code and the multi-economy yield curve data, are available online.

stat.ME↗

arXiv2015

Predicting Melbourne Ambulance Demand using Kernel Warping

Predicting ambulance demand accurately in fine resolutions in space and time is critical for ambulance fleet management and dynamic deployment. Typical challenges include data sparsity at high resolutions and the need to respect complex urban spatial domains. To provide spatial density predictions for ambulance demand in Melbourne, Australia as it varies over hourly intervals, we propose a predictive spatio-temporal kernel warping method. To predict for each hour, we build a kernel density estimator on a sparse set of the most similar data from relevant past time periods (labeled data), but warp these kernels to a larger set of past data irregardless of time periods (point cloud). The point cloud represents the spatial structure and geographical characteristics of Melbourne, including complex boundaries, road networks, and neighborhoods. Borrowing from manifold learning, kernel warping is performed through a graph Laplacian of the point cloud and can be interpreted as a regularization towards, and a prior imposed, for spatial features. Kernel bandwidth and degree of warping are efficiently estimated via cross-validation, and can be made time- and/or location-specific. Our proposed model gives significantly more accurate predictions compared to a current industry practice, an unwarped kernel density estimation, and a time-varying Gaussian mixture model.

stat.AP↗

arXiv2015

Predicting Ambulance Demand: a Spatio-Temporal Kernel Approach

Predicting ambulance demand accurately at fine time and location scales is critical for ambulance fleet management and dynamic deployment. Large-scale datasets in this setting typically exhibit complex spatio-temporal dynamics and sparsity at high resolutions. We propose a predictive method using spatio-temporal kernel density estimation (stKDE) to address these challenges, and provide spatial density predictions for ambulance demand in Toronto, Canada as it varies over hourly intervals. Specifically, we weight the spatial kernel of each historical observation by its informativeness to the current predictive task. We construct spatio-temporal weight functions to incorporate various temporal and spatial patterns in ambulance demand, including location-specific seasonalities and short-term serial dependence. This allows us to draw out the most helpful historical data, and exploit spatio-temporal patterns in the data for accurate and fast predictions. We further provide efficient estimation and customizable prediction procedures. stKDE is easy to use and interpret by non-specialized personnel from the emergency medical service industry. It also has significantly higher statistical accuracy than the current industry practice, with a comparable amount of computational expense.

stat.AP↗

arXiv2015

Change Points via Probabilistically Pruned Objectives

The concept of homogeneity plays a critical role in statistics, both in its applications as well as its theory. Change point analysis is a statistical tool that aims to attain homogeneity within time series data. This is accomplished through partitioning the time series into a number of contiguous homogeneous segments. The applications of such techniques range from identifying chromosome alterations to solar flare detection. In this manuscript we present a general purpose search algorithm called cp3o that can be used to identify change points in multivariate time series. This new search procedure can be applied with a large class of goodness of fit measures. Additionally, a reduction in the computational time needed to identify change points is accomplish by means of probabilistic pruning. With mild assumptions about the goodness of fit measure this new search algorithm is shown to generate consistent estimates for both the number of change points and their locations, even when the number of change points increases with the time series length. A change point algorithm that incorporates the cp3o search algorithm and E-Statistics, e-cp3o, is also presented. The only distributional assumption that the e-cp3o procedure makes is that the absolute $α$th moment exists, for some $α\in(0,2)$. Due to this mild restriction, the e-cp3o procedure can be applied to a majority of change point problems. Furthermore, even with such a mild restriction, the e-cp3o procedure has the ability to detect any type of distributional change within a time series. Simulation studies are used to compare the e-cp3o procedure to other parametric and nonparametric change point procedures, we highlight applications of e-cp3o to climate and financial datasets.

stat.ME↗

arXiv2014

Leveraging Cloud Data to Mitigate User Experience from "Breaking Bad"

Low latency and high availability of an app or a web service are key, amongst other factors, to the overall user experience (which in turn directly impacts the bottomline). Exogenic and/or endogenic factors often give rise to breakouts in cloud data which makes maintaining high availability and delivering high performance very challenging. Although there exists a large body of prior research in breakout detection, existing techniques are not suitable for detecting breakouts in cloud data owing to being not robust in the presence of anomalies. To this end, we developed a novel statistical technique to automatically detect breakouts in cloud data. In particular, the technique employs Energy Statistics to detect breakouts in both application as well as system metrics. Further, the technique uses robust statistical metrics, viz., median, and estimates the statistical significance of a breakout through a permutation test. To the best of our knowledge, this is the first work which addresses breakout detection in the presence of anomalies. We demonstrate the efficacy of the proposed technique using production data and report Precision, Recall and F-measure measure. The proposed technique is 3.5 times faster than a state-of-the-art technique for breakout detection and is being currently used on a daily basis at Twitter.

stat.ME↗