Multiple Testing of Local Extrema for Detection of Change Points
Compute convolution function using FFT
Plot data sequence, the first and second-order derivatives, and their ...
Multiple testing of change points for kernel smoothed data
Detection of change points based on 'dSTEM' algorithm
Identify pairwise local maxima and local minima of the second-order de...
Estimate variance of smoothed Gaussian noise
Estimate piecewise slope for piecewise linear model
Compute TPR and FPR
Compute FDR threshold based on Benjamini-Hochberg (BH) algorithm
Generate simulated signals
Smoothing data using Gaussian kernel
Compute SNR of a certain change point location
Find local maxima and local minima of data sequence
Simultaneously detect the number and locations of change points in piecewise linear models under stationary Gaussian noise allowing autocorrelated random noise. The core idea is to transform the problem of detecting change points into the detection of local extrema (local maxima and local minima)through kernel smoothing and differentiation of the data sequence, see Cheng et al. (2020) <doi:10.1214/20-EJS1751>. A low-computational and fast algorithm call 'dSTEM' is introduced to detect change points based on the 'STEM' algorithm in D. Cheng and A. Schwartzman (2017) <doi:10.1214/16-AOS1458>.