not: Narrowest-Over-Threshold Change-Point Detection

Provides efficient implementation of the Narrowest-Over-Threshold methodology for detecting an unknown number of change-points occurring at unknown locations in one-dimensional data following 'deterministic signal + noise' model. Currently implemented scenarios are: piecewise-constant signal, piecewise-constant signal with a heavy-tailed noise, piecewise-linear signal, piecewise-quadratic signal, piecewise-constant signal and with piecewise-constant variance of the noise.

Author
Rafal Baranowski, Yining Chen, Piotr Fryzlewicz
Date of publication
2016-08-23 23:15:50
Maintainer
Rafal Baranowski <r.baranowski@lse.ac.uk>
License
GPL-2
Version
1.0

View on CRAN

Man pages

aic.penalty
Akaike Information Criterion penalty
features
Extract locations of features from a 'not' object
loglik.not
Extract likelihood from a 'not' object
not
Narrowest-Over-Threshold Change-Point Detection
not-package
Narrowest-Over-Threshold Change-Point Detection
plot.not
Plot a 'not' object
predict.not
Estimate signal for a 'not' object.
random.intervals
Generate random intervals
residuals.not
Extract residuals from a 'not' object
sic.penalty
Schwarz Information Criterion penalty

Files in this package

not
not/src
not/src/Makevars
not/src/changepoints_tree.h
not/src/contrasts.c
not/src/not.c
not/src/contrasts.h
not/src/not.h
not/src/changepoints_tree.c
not/NAMESPACE
not/R
not/R/logLik.R
not/R/penalties.R
not/R/plot.R
not/R/predict.R
not/R/not.R
not/R/random.intervals.R
not/R/features.R
not/R/residuals.R
not/MD5
not/DESCRIPTION
not/man
not/man/plot.not.Rd
not/man/aic.penalty.Rd
not/man/residuals.not.Rd
not/man/loglik.not.Rd
not/man/features.Rd
not/man/sic.penalty.Rd
not/man/random.intervals.Rd
not/man/not-package.Rd
not/man/not.Rd
not/man/predict.not.Rd