Detecting and localising changes in different environments.

Abstract: A key assumption in many statistical problems is ``i.i.d.’’, that is to assume data are independent and identically distributed. This is hardly true in real data. One way to relax this assumption is to assume data are piecewise stationary, over a time series or more generally over a graph. This is the motivation of the change point analysis. In this talk I will give a general overview of the change point analysis, revolving around two fundamental questions and covering a range of different examples.

Bio: I am a Reader in the Department of Statistics, University of Warwick and a Turing Fellow at the Alan Turing Institute, previously an Associate Professor in the University of Warwick, a Lecturer in the University of Bristol, a postdoc of Professor Richard Samworth and a graduate student of Professor Zhiliang Ying. I obtained my academic degrees from Fudan University (B.Sc. in Mathematics, June 2009 and Ph.D. in Mathematical Statistics, June 2013).