A combined SR-CUSUM procedure for detecting common changes in panel data

Abstract A procedure based on the sum of N Shiryayev–Roberts processes is proposed to detect common changes in panel data and shown to perform better for small portions of changed panels. The change-point for each panel is estimated by using the CUSUM process calculated in parallel. The changed panels are isolated by using the scores formed by the post-change parameter estimations and the common change point is then estimated from the isolated changed panels. A real example is used for illustration. An adaptive detection procedures is also proposed when the unknown post-change parameters are estimated adaptively in each panel.

[1]  Yanhong Wu.  Inference for Change Point and Post Change Means After a CUSUM Test , 2005 .

[2]  C. Klüppelberg,et al.  Modelling Extremal Events , 1997 .

[3]  P. Hall,et al.  Innovated Higher Criticism for Detecting Sparse Signals in Correlated Noise , 2009, 0902.3837.

[4]  Hock Peng Chan,et al.  Optimal sequential detection in multi-stream data , 2015, 1506.08504.

[5]  Yanhong Wu,et al.  SUPPLEMENTARY SCORE TEST IN MIXTURE MODEL , 2002 .

[6]  Arjun K. Gupta,et al.  Local score tests in mixture exponential family , 2003 .

[7]  Hongzhe Li,et al.  Simultaneous Discovery of Rare and Common Segment Variants. , 2013, Biometrika.

[8]  Aleksey S. Polunchenko.  On the quasi-stationary distribution of the Shiryaev–Roberts diffusion , 2016, 1606.06658.

[9]  D. Siegmund.  Detecting Simultaneous Change-points in Multiple Sequences , 2008 .

[10]  Nancy R. Zhang,et al.  Detecting simultaneous changepoints in multiple sequences. , 2010, Biometrika.

[11]  David Siegmund,et al.  Sequential multi-sensor change-point detection , 2013, 2013 Information Theory and Applications Workshop (ITA).

[12]  D. Siegmund,et al.  A diffusion process and its applications to detecting a change in the drift of Brownian motion , 1984 .

[13]  D. Donoho,et al.  Higher criticism for detecting sparse heterogeneous mixtures , 2004, math/0410072.

[14]  Yanhong Wu.  Detecting changes in a multiparameter exponential family by using adaptive CUSUM procedure , 2017 .

[15]  Y. Mei.  Efficient scalable schemes for monitoring a large number of data streams , 2010 .

[16]  Moshe Pollak,et al.  Sequential Change-Point Detection Procedures That are Nearly Optimal and Computationally Simple , 2008 .

[17]  M. Pollak,et al.  Nonanticipating estimation applied to sequential analysis and changepoint detection , 2005, math/0507434.

[18]  D. Siegmund.  Sequential Analysis: Tests and Confidence Intervals , 1985 .

[19]  J. Corcoran.  Modelling Extremal Events for Insurance and Finance , 2002 .

[20]  M. Pollak.  Average Run Lengths of an Optimal Method of Detecting a Change in Distribution. , 1987 .

[21]  Nancy R. Zhang,et al.  Detecting simultaneous variant intervals in aligned sequences , 2011, 1108.3177.

[22]  Yajun Mei,et al.  Large-Scale Multi-Stream Quickest Change Detection via Shrinkage Post-Change Estimation , 2015, IEEE Transactions on Information Theory.

[23]  J. Andel.  Sequential Analysis , 2022, The SAGE Encyclopedia of Research Design.

[24]  Hock Peng Chan,et al.  Detection of spatial clustering with average likelihood ratio test statistics , 2009, 0911.3769.

[25]  H. Chan,et al.  Optimal detection of multi-sample aligned sparse signals , 2015, 1510.03659.

[26]  V. Veeravalli,et al.  Asymptotically Optimal Quickest Change Detection in Distributed Sensor Systems , 2008 .