CPQt
Overview
CPQt is an application which allows you to model an unknown number of abrupt changes in the mean value of one or more data series, with either known or unknown errors on the individual data series. When more than one data set is used, it is assumed that the changepoint locations will be the same for all data sets. The mathematical approach underlying CPQt is transdimensional Markov Chain Monte Carlo (MCMC) and the details are given in Gallagher et al. (2011), referenced below.
A program user guide in PDF form is available:
CPQt_Documentation.pdf 1.3MB.
The code is not available here however it can be downloaded
from the author's web site using these instructions:
Accessing QTQt and BayesMixQT
for Windows or Macintosh.pdf sic 670KB.
References
- Gallagher, K., Bodin, T. Sambridge, M, Weiss, D, Kylander, M, and Large, D. "Inference of abrupt changes in noisy geochemical records using Bayesian transdimensional changepoint models", Earth Planet. Sci. Letts., 311, 182-194 182-194 doi:10.1016/j.epsl.2011.09.015, (2011)