Student Seminar Series
DATE: Wednesday March 15th, 12:00pm
LOCATION: MSB 1143 (Statistics Seminar Room).
SPEAKERS: Hao Chen, Assistant Professor, Statistics, UC Davis
TITLE: “Change-point detection for locally dependent data”
ABSTRACT: In a sequence of multivariate observations or object data, such as networks, local dependence is common and could lead to false change-point discoveries. We propose a new way of permutation, circular block permutation with a random starting point, to address this problem. This permutation scheme is studied on a non-parametric change-point detection framework that utilizes similarity information among the observations, resulting in a generic framework for change-point analysis for locally dependent data. We also derive an analytic formula to approximate the significance of the test, making the method fast applicable to long data sequences.
This seminar series is organized by PhD Students Irene Kim and Ozan Sonmez.