Consistent multiple testing for change points

Kuo mei Chen, Arthur Cohen, Harold Sackrowitz

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


The change point problem for independent normal means is considered as a multiple testing problem. Two stepwise methods are considered. Namely, the binary segmentation method of Vostrikova (1981) [7] and the maximum residual down method of Cohen et al. (2009) [5]. Both of these methods are shown to be consistent. Consistent here means that as sample sizes tend to infinity, the probability of making an error (false rejection or false acceptance) tends to zero.

Original languageEnglish (US)
Pages (from-to)1339-1343
Number of pages5
JournalJournal of Multivariate Analysis
Issue number10
StatePublished - Nov 2011

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty


  • Binary sequential segmentation
  • Familywise error rate
  • Maximum residual down
  • Primary
  • Secondary
  • Stepdown procedures


Dive into the research topics of 'Consistent multiple testing for change points'. Together they form a unique fingerprint.

Cite this