An evaluation of change-point estimators for a sequence of normal observations with unknown parameters

Jorge Garza-Venegas, Victor Tercero-Gomez, Alvaro Cordero Franco, María Temblador-Pérez, Mario Beruvides

Research output: Contribution to journalArticlepeer-review

Abstract

Performance of maximum likelihood estimators (MLE) of the change-point in normal series is evaluated considering three scenarios where process parameters are assumed to be unknown. Different shifts, sample sizes, and locations of a change-point were tested. A comparison is made with estimators based on cumulative sums and Bartlett's test. Performance analysis done with extensive simulations for normally distributed series showed that the MLEs perform better (or equal) in almost every scenario, with smaller bias and standard error. In addition, robustness of MLE to non-normality is also studied.

Original languageEnglish
Pages (from-to)4297-4317
Number of pages21
JournalCommunications in Statistics: Simulation and Computation
Volume46
Issue number6
DOIs
StatePublished - Jul 3 2017

Keywords

  • Bartlett's test
  • CUSUM
  • MLE
  • Robustness
  • Unknown parameters

Fingerprint Dive into the research topics of 'An evaluation of change-point estimators for a sequence of normal observations with unknown parameters'. Together they form a unique fingerprint.

Cite this