首页 | 本学科首页   官方微博 | 高级检索  
     检索      


CUSUM chart for detecting range shifts when monotonicity of likelihood ratio is invalid
Authors:Guanfu Liu  Xiaolong Pu  Lei Wang
Institution:School of Finance and Statistics, East China Normal University, No. 500 Dongchuan Road, Shanghai 200241, People's Republic of China
Abstract:It is often encountered in the literature that the log-likelihood ratios (LLR) of some distributions (e.g. the student t distribution) are not monotonic. Existing charts for monitoring such processes may suffer from the fact that the average run length (ARL) curve is a discontinuous function of control limit. It implies that some pre-specified in-control (IC) ARLs of these charts may not be reached. To guarantee the false alarm rate of a control chart lower than the nominal level, a larger IC ARL is usually suggested in the literature. However, the large IC ARL may weaken the performance of a control chart when the process is out-of-control (OC), compared with a just right IC ARL. To overcome it, we adjust the LLR to be a monotonic one in this paper. Based on it, a multiple CUSUM chart is developed to detect range shifts in IC distribution. Theoretical result in this paper ensures the continuity of its ARL curve. Numerical results show our proposed chart performs well under the range shifts, especially under the large shifts. In the end, a real data example is utilized to illustrate our proposed chart.
Keywords:MACUSUM chart  multiple charts  CUSUM chart  RLCUSUM  heavy-tailed distribution  range shifts
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号