|
Activity Number:
|
201
- Estimation and Inference in Complex Systems
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 8, 2022 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
IMS
|
|
Abstract #322059
|
|
|
Title:
|
Sequential Common Rate Change Detection, Isolation, and Estimation in Multiple Poisson Processes
|
|
Author(s):
|
Yanhong Wu* and Wei Biao Wu
|
|
Companies:
|
California state university, Stanislaus and University of Chicago
|
|
Keywords:
|
Average run length;
Common change-point detection;
CUSUM process;
FDR and FNR;
Shiryayev-Roberts process
|
|
Abstract:
|
We consider the detection of a common change when multiple independent Poisson processes are monitored simultaneously where only a portion of the processes have rate change after the change time. By calculating the individual CUSUM processes and Shiryayev-Roberts (S-R) processes recursively in parallel, a combined CUSUM-SR procedure is proposed by using the sum of S-R processes as the detection process for a common change and after the detection, the individual CUSUM processes are used to isolate the changed panels with FDR control. The medians of change time estimates based on the individual CUSUM processes or S-R processes from those isolated changed panels are then used to estimate the common change time. Accurate approximation for the average in-control length is obtained for the design of the detection process. Exponential approximations for the CUSUM processes at the detection time are used for the p-value calculation. Mining disaster data in USA from different states and different causes are used for illustrations.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2022 program
|
