mosum: A package for moving sums in change point analysis

Haeran Cho, Claudia Kirch, Alexander Meier

Research output: Contribution to journalArticle (Academic Journal)peer-review

162 Downloads (Pure)

Abstract

Understanding changes plays a crucial role in many fields of science, economy, technology and medicine. Whenever time series data, i.e., temporally ordered data, is described by means of a stationary stochastic model, it is of interest to verify the stationarity assumption on the basis of the data, and change point analysis provides mathematical tools for this purpose. A particularly important, and thus widely studied, problem is to detect changes in the mean at unknown time points. In this paper, we present the R package mosum, which implements elegant and mathematically well-justified procedures to themultiple mean change problem using moving sum (MOSUM) statistics.
Original languageEnglish
JournalJournal of Statistical Software
Publication statusAccepted/In press - 8 Sep 2019

Fingerprint Dive into the research topics of 'mosum: A package for moving sums in change point analysis'. Together they form a unique fingerprint.

Cite this