Learn R Programming

VARDetect (version 0.1.8)

Multiple Change Point Detection in Structural VAR Models

Description

Implementations of Thresholded Block Segmentation Scheme (TBSS) and Low-rank plus Sparse Two Step Procedure (LSTSP) algorithms for detecting multiple changes in structural VAR models. The package aims to address the problem of change point detection in piece-wise stationary VAR models, under different settings regarding the structure of their transition matrices (autoregressive dynamics); specifically, the following cases are included: (i) (weakly) sparse, (ii) structured sparse, and (iii) low rank plus sparse. It includes multiple algorithms and related extensions from Safikhani and Shojaie (2020) and Bai, Safikhani and Michailidis (2020) .

Copy Link

Version

Install

install.packages('VARDetect')

Monthly Downloads

72

Version

0.1.8

License

GPL-2

Maintainer

Yue Bai

Last Published

June 15th, 2024

Functions in VARDetect (0.1.8)

prox.sparse.func

Proximal function with l1-norm penalty updating

first.step.detect

First step rolling window function

Main function for the low rank plus sparse structure VAR model

Nuclear norm penalty for low-rank component

Generate VAR(p) model data with break points

plot.VARDetect.result

Plotting the output from VARDetect.result class

Function to deploy simulation with LSTSP algorithm

print.VARDetect.result

Function to print the change points estimated by VARDetect

Plot the AR coefficient matrix

Shrinkage function for sparse soft-thresholding

prox.nuclear.func.fLS

Proximal function for nuclear norm penalty

Shrinkage function for low-rank soft-thresholding

Prediction function (block)

Simulation function for TBSS algorithm

Prediction function (single observation)

first.step.blocks.group

block fused sparse group lasso step (first step).

Objective function

L1-norm penalty for sparse component

summary.VARDetect.result

Function to summarize the change points estimated by VARDetect

weekly stock price data

A function to solve low rank plus sparse model estimation using FISTA algorithm

remove.extra.pts

helper function for detection check

Function to plot the sparsity levels for estimated model parameters

Function to plot Granger causality networks

second.step.detect

Backward elimination algorithm for screening in the second step

prox.nuclear.func

Proximal function with nuclear norm penalty updating

second.step.local

local screening step (second step).

Block segmentation scheme (BSS).

summary.VARDetect.simu.result

A function to summarize the results for simulation

third.step.exhaustive.search

Exhaustive search step (third step).

detection_check

Function for detection performance check

EEG signal data

cluster the points by neighborhood size a_n

backward.selection

Backward selection function for the second screening step

Auxiliary function to calculate loss at the estimated change points

Single change point detection for low-rank plus sparse model with cross-validation

Single change point detection for low-rank plus sparse model structure

break.var.local.new

Compute local loss function.

Gradient function of quardratic loss

first.step.blocks

block fused lasso step (first step for BSS).

cross-validation index function, separate train and test sets

cv.tuning.selection

a function to apply cross-validation to select tuning parameter by minimizing SSE

Evaluation function, return the performance of simulation results

hausdorff_check

Function for Hausdorff distance computation

Select the lag of the VAR model using total BIC method

A helper function for implementing FISTA algorithm to estimate low-rank matrix

Main loss function for quardratic loss

An auxiliary function in FISTA algorithm

BIC and HBIC function