TY - JOUR
T1 - An evaluation of change-point estimators for a sequence of normal observations with unknown parameters
AU - Garza-Venegas, Jorge
AU - Tercero-Gomez, Victor
AU - Cordero Franco, Alvaro
AU - Temblador-Pérez, María
AU - Beruvides, Mario
N1 - Publisher Copyright:
© 2017 Taylor & Francis Group, LLC.
PY - 2017/7/3
Y1 - 2017/7/3
N2 - 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.
AB - 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.
KW - Bartlett's test
KW - CUSUM
KW - MLE
KW - Robustness
KW - Unknown parameters
UR - http://www.scopus.com/inward/record.url?scp=85011883110&partnerID=8YFLogxK
U2 - 10.1080/03610918.2015.1115524
DO - 10.1080/03610918.2015.1115524
M3 - Article
AN - SCOPUS:85011883110
SN - 0361-0918
VL - 46
SP - 4297
EP - 4317
JO - Communications in Statistics: Simulation and Computation
JF - Communications in Statistics: Simulation and Computation
IS - 6
ER -