L2 Inference for Change Points in High-Dimensional Time Series
Check the validity of the neighbourhood specification
Construct an S3 class 'no_nbd' or 'nbd' for change-point estimation
Generate a random Gaussian vector
Obtain the time-stamps and spatial locations with breaks
Obtain the time-stamps and spatial locations without break
Obtain the time-stamps and spatial locations with breaks
The covariance matrix for generating random Gaussian vector
Obtain critical values and threshold
Obtain critical values and threshold
Obtain critical values and threshold
Obtain the simulated standardised gap vector
Obtain the simulated standardised gap vector
Obtain the simulated standardised gap vector
Compute the long-run variance of the gap vector
Obtain the test statistics
Obtain the test statistics
Obtain the test statistics
Obtain the standardised gap vector
Obtain the standardised gap vector
Obtain the standardised gap vector
Estimate the time-stamps and spatial locations with breaks
Plot the time series and change-points
Plot the time series and change-points
Plot the time series and change-points
Simulate data with neighbourhood
Simulate data without neighbourhood
Summarize the estimation results
Summarize the estimation results
Test the existence of change-points in the data
'no_nbd' or 'nbd' object construction
Provides a method for detecting multiple change points in high-dimensional time series, targeting dense or spatially clustered signals. See Li et al. (2023) "L2 Inference for Change Points in High-Dimensional Time Series via a Two-Way MOSUM". arXiv preprint <arXiv:2208.13074>.