Joint Financial Mathematics & Statistics Seminar: Professor David Allen -- Nonparametric Multiple Change Point Analysis of the Global Financial Crisis

Abstract

   This paper presents an application of a recently developed approach by
   Matteson and James (2012) for the analysis of change points in a data set,
   namely major ?financial market indices converted to ?financial return series.
   The general problem concerns the inference of a change in the distribution
   of a set of time-ordered variables. The approach involves the nonparametric
   estimation of both the number of change points and the positions at which
   they occur. The approach is general and does not involve assumptions about
   the nature of the distributions involved or the type of change beyond the 
   assumption of the existence of the absolute moment, for some 2 (0; 2). The 
   estimation procedure is based on hierarchical clustering and the application 
   of both divisive and agglomeration algorithms. The method is used to evaluate 
   the impact of the Global Financial Crisis (GFC) on the US, French, German, UK, 
   Japanese and Chinese markets, as represented by the S&P500, CAC, DAX, FTSE All Share,
   Nikkei 225 and Shanghai A share Indices, respectively, from 2003 to 2013.
   The approach is used to explore the timing and number of change points in
   the data sets corresponding to the GFC and subsequent European Debt Crisis.