An R Package for Multiple Break-Point Detection via the Cross-Entropy Method

Implements the Cross-Entropy (CE) method, which is a model based stochastic optimization technique to estimate both the number and their corresponding locations of break-points in continuous and discrete measurements (Priyadarshana and Sofronov (2015), Priyadarshana and Sofronov (2012a), Priyadarshana and Sofronov (2012b)).


News

1.2 2016-01-12 o More refinements to the exisiting functions with added functionalities. User can specify the initial locations to obtain more precise estimates of the locations. o Different model selection criteria are now supported (BIC/AIC/mBIC). o In continuous data, both changes in mean and variances can now be estimated.

1.1 2014-12-21 o Bug fixes and added new functionalities to detect break-points in over-dispersed count data.

1.0 2014-01-17 o Version 1.0 of the breakpoint package was submitted.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("breakpoint")

1.2 by Priyadarshana W.J.R.M., 2 years ago


https://github.com/madawaweer/breakpoint


Browse source code at https://github.com/cran/breakpoint


Authors: Priyadarshana W.J.R.M. and Georgy Sofronov


Documentation:   PDF Manual  


GPL (>= 2) license


Imports ggplot2, MASS, msm, foreach, parallel, doParallel


See at CRAN