CMStatistics 2016: Start Registration
View Submission - CMStatistics
B1339
Title: A general approach to the analysis of statistics from subsamples Authors:  Stanislav Volgushev - University of Toronto (Canada) [presenting]
Xiaofeng Shao - University of Illinois at Urbana-Champaign (United States)
Abstract: In time series analysis, statistics based on collections of estimators computed from subsamples play a role in many applications. Proving results about the joint asymptotic distribution of such statistics is challenging, since it typically involves a nontrivial verification of technical conditions and tedious case-by-case asymptotic analysis. We provide a technique that allows us to circumvent those problems in a general setting. Our approach consists of two major steps: a probabilistic part which is mainly concerned with weak convergence of sequential empirical processes, and an analytic part providing general ways to extend this weak convergence to smooth functionals of the sequential empirical process. The methodology is illustrated for several examples such as self-normalization and change-point detection.