CMStatistics 2016: Start Registration
View Submission - CMStatistics
B1169
Title: Inference for the cross covariance of stationary functional time series Authors:  Gregory Rice - University of Waterloo (Canada) [presenting]
Abstract: When considering two or more time series of functions, for example those derived from densely observed intraday stock price data of several companies, one commonly wishes to understand the dependence structure across series. This can be measured by means of the empirical cross covariance operator, but statistical procedures for measuring the significance of such estimators are limited. We present methodology for conducting statistical inference on the cross covariance operator estimated between two stationary functional time series. Two separate problems are considered: testing for a specified cross covariance structure, and testing for a single change point in the cross covariance within the sample.