Forgetting Factor Methods for Change Detection in Streaming Data

An implementation of the adaptive forgetting factor scheme described in Bodenham and Adams (2016) which adaptively estimates the mean and variance of a stream in order to detect multiple changepoints in streaming data. The implementation is in C++ and uses Rcpp. Additionally, implementations of the fixed forgetting factor scheme from the same paper, as well as the classic CUSUM and EWMA methods, are included.


ffstream 1.6.0


  • Changed maintainer URL to [email protected]. This is simply to create a centralised email for my packages.
  • Fixed compilation issue with Rcpp, which seemed to occur due to a new version changing the NAMESPACE file.
  • Fixed a bug that seemed to occur when the burn-in length was set to zero for the AFF change detector, i.e. BL=0 case.
  • Changed name of vignette to intro and created ffstream_vignette() function; it seemed that many users did not know this vignette existed, so hopefully the creation of the new function will change that.
  • In the DESCRIPTION added URL for 'full' vignette hosted on GitHub. Still cannot figure out why I need to make the figures so small in size, but other vignettes seem to be able to have larger figures. At least this allows users to see the full vignette.
  • Modified the ffstream() function, which was previously kind of a placeholder to inform the user about the ffstream_vignette function, as well as the URL for the full vignette.
  • Added ability to obtain Lderiv from an affcd object.
  • Finally, changed the required R version to 3.5.0; probably not necessary, but this is what it was built on, so apologies to any users that need to then upgrade. Also upgraded requirements for Rcpp and testtthat.

Reference manual

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


0.1.6 by Dean Bodenham, 2 years ago

Browse source code at

Authors: Dean Bodenham

Documentation:   PDF Manual  

GPL-2 | GPL-3 license

Imports methods

Depends on Rcpp

Suggests testthat, knitr, rmarkdown

Linking to Rcpp

See at CRAN