Learn R Programming

VARcpDetectOnline (version 0.2.0)

Sequential Change Point Detection for High-Dimensional VAR Models

Description

Implements the algorithm introduced in Tian, Y., and Safikhani, A. (2024) , "Sequential Change Point Detection in High-dimensional Vector Auto-regressive Models". This package provides tools for detecting change points in the transition matrices of VAR models, effectively identifying shifts in temporal and cross-correlations within high-dimensional time series data.

Copy Link

Version

Install

install.packages('VARcpDetectOnline')

Monthly Downloads

175

Version

0.2.0

License

GPL-2 | file LICENSE

Issues

Pull Requests

Stars

Forks

Maintainer

Yuhan Tian

Last Published

February 13th, 2025

Functions in VARcpDetectOnline (0.2.0)

cvVAR_ENET

Cross Validation for Elastic Net VAR Estimation
VAR_cpDetect_Online

VAR_cpDetect_Online: Sequential change point Detection for Vector Auto-Regressive Models
get_cps

Identify the Beginning of the Alarm Clusters
fitVAR

Fit VAR Model with Elastic Net via Cross Validation
generateVAR

Generate VAR Data
sp500

S&P 500 Daily Log Returns and Corresponding Dates
computeResiduals

Compute VAR Model Residuals
duplicateMatrix

Construct Lagged Design Matrix for VAR
transformData

Transform Data for VAR Estimation
applyThreshold

Apply Thresholding to VAR Coefficients
cvVAR

Cross-Validated VAR Estimation using Elastic Net
splitMatrix

Split Coefficient Matrix into VAR Lags
estimateCovariance

Estimate Covariance Matrix from Residuals