skip to main content


Title: Fast and Scalable Algorithm for Detection of Structural Breaks in Big VAR Models
Many real time series datasets exhibit structural changes over time. A popular model for capturing their temporal dependence is that of vector autoregressions (VAR), which can accommodate structural changes through time evolving transition matrices. The problem then becomes to both estimate the (unknown) number of structural break points, together with the VAR model parameters. An additional challenge emerges in the presence of very large datasets, namely on how to accomplish these two objectives in a computational efficient manner. In this article, we propose a novel procedure which leverages a block segmentation scheme (BSS) that reduces the number of model parameters to be estimated through a regularized least-square criterion. Specifically, BSS examines appropriately defined blocks of the available data, which when combined with a fused lasso-based estimation criterion, leads to significant computational gains without compromising on the statistical accuracy in identifying the number and location of the structural breaks. This procedure is further coupled with new local and exhaustive search steps to consistently estimate the number and relative location of the break points. The procedure is scalable to big high-dimensional time series datasets with a computational complexity that can achieve O(n), where n is the length of the time series (sample size), compared to an exhaustive procedure that requires steps. Extensive numerical work on synthetic data supports the theoretical findings and illustrates the attractive properties of the procedure. Finally, an application to a neuroscience dataset exhibits its usefulness in applications. Supplementary files for this article are available online.  more » « less
Award ID(s):
1830175
NSF-PAR ID:
10312308
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Journal of Computational and Graphical Statistics
ISSN:
1061-8600
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    A factor-augmented vector autoregressive (FAVAR) model is defined by a VAR equation that captures lead-lag correlations amongst a set of observed variables X and latent factors F, and a calibration equation that relates another set of observed variables Y with F and X. The latter equation is used to estimate the factors that are subsequently used in estimating the parameters of the VAR system. The FAVAR model has become popular in applied economic research, since it can summarize a large number of variables of interest as a few factors through the calibration equation and subsequently examine their influence on core variables of primary interest through the VAR equation. However, there is increasing need for examining lead-lag relationships between a large number of time series, while incorporating information from another high-dimensional set of variables. Hence, in this paper we investigate the FAVAR model under high-dimensional scaling. We introduce an appropriate identification constraint for the model parameters, which when incorporated into the formulated optimization problem yields estimates with good statistical properties. Further, we address a number of technical challenges introduced by the fact that estimates of the VAR system model parameters are based on estimated rather than directly observed quantities. The performance of the proposed estimators is evaluated on synthetic data. Further, the model is applied to commodity prices and reveals interesting and interpretable relationships between the prices and the factors extracted from a set of global macroeconomic indicators. 
    more » « less
  2. A factor-augmented vector autoregressive (FAVAR) model is defined by a VAR equation that captures lead-lag correlations amongst a set of observed variables X and latent factors F, and a calibration equation that relates another set of observed variables Y with F and X. The latter equation is used to estimate the factors that are subsequently used in estimating the parameters of the VAR system. The FAVAR model has become popular in applied economic research, since it can summarize a large number of variables of interest as a few factors through the calibration equation and subsequently examine their influence on core variables of primary interest through the VAR equation. However, there is increasing need for examining lead-lag relationships between a large number of time series, while incorporating information from another high-dimensional set of variables. Hence, in this paper we investigate the FAVAR model under high-dimensional scaling. We introduce an appropriate identification constraint for the model parameters, which when incorporated into the formulated optimization problem yields estimates with good statistical properties. Further, we address a number of technical challenges introduced by the fact that estimates of the VAR system model parameters are based on estimated rather than directly observed quantities. The performance of the proposed estimators is evaluated on synthetic data. Further, the model is applied to commodity prices and reveals interesting and interpretable relationships between the prices and the factors extracted from a set of global macroeconomic indicators. 
    more » « less
  3. Summary

    The bootstrap provides a simple and powerful means of assessing the quality of estimators. However, in settings involving large data sets—which are increasingly prevalent—the calculation of bootstrap-based quantities can be prohibitively demanding computationally. Although variants such as subsampling and the m out of n bootstrap can be used in principle to reduce the cost of bootstrap computations, these methods are generally not robust to specification of tuning parameters (such as the number of subsampled data points), and they often require knowledge of the estimator's convergence rate, in contrast with the bootstrap. As an alternative, we introduce the ‘bag of little bootstraps’ (BLB), which is a new procedure which incorporates features of both the bootstrap and subsampling to yield a robust, computationally efficient means of assessing the quality of estimators. The BLB is well suited to modern parallel and distributed computing architectures and furthermore retains the generic applicability and statistical efficiency of the bootstrap. We demonstrate the BLB's favourable statistical performance via a theoretical analysis elucidating the procedure's properties, as well as a simulation study comparing the BLB with the bootstrap, the m out of n bootstrap and subsampling. In addition, we present results from a large-scale distributed implementation of the BLB demonstrating its computational superiority on massive data, a method for adaptively selecting the BLB's tuning parameters, an empirical study applying the BLB to several real data sets and an extension of the BLB to time series data.

     
    more » « less
  4. Lateral stiffness of structural components, such as reinforced concrete (RC) columns, plays an important role in resisting the lateral earthquake loads. The lateral stiffness relates the lateral force to the lateral deformation, having a critical effect on the accuracy of the lateral seismic response predictions. The classical methods (e.g. fiber beam–column model) to estimate the lateral stiffness require calculations from section, element, and structural levels, which is time-consuming. Moreover, the shear deformation and bond-slip effect may also need to be included to more accurately calculate the lateral stiffness, which further increases the modeling difficulties and the computational cost. To reduce the computational time and enhance the accuracy of the predictions, this article proposes a novel data-driven method to predict the laterally seismic response based on the estimated lateral stiffness. The proposed method integrates the machine learning (ML) approach with the hysteretic model, where ML is used to compute the parameters that govern the nonlinear properties of the lateral response of target structural components directly from a training set composed of experimental data (i.e. data-driven procedure) and the hysteretic model is used to directly output the lateral stiffness based on the computed parameters and then to perform the seismic analysis. We apply the proposed method to predict the lateral seismic response of various types of RC columns subjected to cyclic loading and ground motions. We present the detailed model formulation for the application, including the developments of a modified hysteretic model, a hybrid optimization algorithm, and two data-driven seismic response solvers. The results predicted by the proposed method are compared with those obtained by classical methods with the experimental data serving as the ground truth, showing that the proposed method significantly outperforms the classical methods in both generalized prediction capabilities and computational efficiency.

     
    more » « less
  5. INTRODUCTION Transposable elements (TEs), repeat expansions, and repeat-mediated structural rearrangements play key roles in chromosome structure and species evolution, contribute to human genetic variation, and substantially influence human health through copy number variants, structural variants, insertions, deletions, and alterations to gene transcription and splicing. Despite their formative role in genome stability, repetitive regions have been relegated to gaps and collapsed regions in human genome reference GRCh38 owing to the technological limitations during its development. The lack of linear sequence in these regions, particularly in centromeres, resulted in the inability to fully explore the repeat content of the human genome in the context of both local and regional chromosomal environments. RATIONALE Long-read sequencing supported the complete, telomere-to-telomere (T2T) assembly of the pseudo-haploid human cell line CHM13. This resource affords a genome-scale assessment of all human repetitive sequences, including TEs and previously unknown repeats and satellites, both within and outside of gaps and collapsed regions. Additionally, a complete genome enables the opportunity to explore the epigenetic and transcriptional profiles of these elements that are fundamental to our understanding of chromosome structure, function, and evolution. Comparative analyses reveal modes of repeat divergence, evolution, and expansion or contraction with locus-level resolution. RESULTS We implemented a comprehensive repeat annotation workflow using previously known human repeats and de novo repeat modeling followed by manual curation, including assessing overlaps with gene annotations, segmental duplications, tandem repeats, and annotated repeats. Using this method, we developed an updated catalog of human repetitive sequences and refined previous repeat annotations. We discovered 43 previously unknown repeats and repeat variants and characterized 19 complex, composite repetitive structures, which often carry genes, across T2T-CHM13. Using precision nuclear run-on sequencing (PRO-seq) and CpG methylated sites generated from Oxford Nanopore Technologies long-read sequencing data, we assessed RNA polymerase engagement across retroelements genome-wide, revealing correlations between nascent transcription, sequence divergence, CpG density, and methylation. These analyses were extended to evaluate RNA polymerase occupancy for all repeats, including high-density satellite repeats that reside in previously inaccessible centromeric regions of all human chromosomes. Moreover, using both mapping-dependent and mapping-independent approaches across early developmental stages and a complete cell cycle time series, we found that engaged RNA polymerase across satellites is low; in contrast, TE transcription is abundant and serves as a boundary for changes in CpG methylation and centromere substructure. Together, these data reveal the dynamic relationship between transcriptionally active retroelement subclasses and DNA methylation, as well as potential mechanisms for the derivation and evolution of new repeat families and composite elements. Focusing on the emerging T2T-level assembly of the HG002 X chromosome, we reveal that a high level of repeat variation likely exists across the human population, including composite element copy numbers that affect gene copy number. Additionally, we highlight the impact of repeats on the structural diversity of the genome, revealing repeat expansions with extreme copy number differences between humans and primates while also providing high-confidence annotations of retroelement transduction events. CONCLUSION The comprehensive repeat annotations and updated repeat models described herein serve as a resource for expanding the compendium of human genome sequences and reveal the impact of specific repeats on the human genome. In developing this resource, we provide a methodological framework for assessing repeat variation within and between human genomes. The exhaustive assessment of the transcriptional landscape of repeats, at both the genome scale and locally, such as within centromeres, sets the stage for functional studies to disentangle the role transcription plays in the mechanisms essential for genome stability and chromosome segregation. Finally, our work demonstrates the need to increase efforts toward achieving T2T-level assemblies for nonhuman primates and other species to fully understand the complexity and impact of repeat-derived genomic innovations that define primate lineages, including humans. Telomere-to-telomere assembly of CHM13 supports repeat annotations and discoveries. The human reference T2T-CHM13 filled gaps and corrected collapsed regions (triangles) in GRCh38. Combining long read–based methylation calls, PRO-seq, and multilevel computational methods, we provide a compendium of human repeats, define retroelement expression and methylation profiles, and delineate locus-specific sites of nascent transcription genome-wide, including previously inaccessible centromeres. SINE, short interspersed element; SVA, SINE–variable number tandem repeat– Alu ; LINE, long interspersed element; LTR, long terminal repeat; TSS, transcription start site; pA, xxxxxxxxxxxxxxxx. 
    more » « less