Distribution properties of the sign statistic for stationary time series data
LE3 .A278 2011
2011
Zhang, Ying
Acadia University
Bachelor of Science
Honours
Mathematics and Statistics
Mathematics & Statistics
The purpose of this thesis is to examine both the asymptotic and the finite sample distribution properties of the sign statistic. Background information is provided on time series, U-statistics are discussed, and some theory involving U-statistics, in particular the sign statistic, is presented and applied. The finite sample distribution of the sign statistic is examined through computer simulation of particular ARMA models. The asymptotic and finite variance of the sign statistic are considered, and a method to use the sign statistic in hypothesis testing is investigated.
The author retains copyright in this thesis. Any substantial copying or any other actions that exceed fair dealing or other exceptions in the Copyright Act require the permission of the author.
https://scholar.acadiau.ca/islandora/object/theses:784