Implements the PELT method for identifying changepoints in a given set of summary statistics for a specified cost function and penalty.
This function is called by cpt.mean, cpt.var and cpt.meanvar when method="PELT". This is not intended for use by regular users of the package. It is exported for developers to call directly for speed increases or to fit alternative cost functions.
WARNING: No checks on arguments are performed!
PELT(sumstat, pen = 0, cost_func = "norm.mean", shape = 1, minseglen = 1)A list is returned with elements:
Vector of length n containing the last changepoint prior to each timepoint.
Ordered list of optimal number of changepoints ending with n.
Vector of lenght n containing the likelihood of the optimal segmentation up to each timepoint.
Number of changes identified.
A matrix containing the summary statistics of data within which you wish to find a changepoint. Currently assumes 3 columns and uses the number of rows as the length of the data +1 (initial value of 0).
Default choice is 0, this should be evaluated elsewhere and a numerical value entered. This should be positive - this isn't checked but results are meaningless if it isn't.
The friendly name of the cost function to be called in C. If using your own cost function, this must be the name of the C function to use.
Only required for cost_func="Gamma",default is 1. Must be a positive value, this isn't checked.
Positive integer giving the minimum segment length (no. of observations between changes), default is 1. No checks are performed on the input value so it could be larger than feasible to have changes in the data.
Rebecca Killick
This function is used as a wrapper function to implement the PELT algorithm in C. It simply creates the necessary worker vectors, ensures all inputs are the correct type, and passes everything to the C function.
This function is exported for developer use only. It does not perform any checks on inputs (other than type coersion) and is simply a wrapper function for the C code.
PELT Algorithm: Killick R, Fearnhead P, Eckley IA (2012) Optimal detection of changepoints with a linear computational cost, JASA 107(500), 1590--1598
CROPS: Haynes K, Eckley IA, Fearnhead P (2014) Efficient penalty search for multiple changepoint problems (in submission), arXiv:1412.3617
cpt.mean,cpt.meanvar,plot-methods,cpt
#This function should only be used by developers, see its use in cpt.mean, cpt.var and cpt.meanvar.
Run the code above in your browser using DataLab