|
Title:
Asymptotic distribution of Cramer-von Mises statistics for ARCH residual empirical processes
Untitled
Author:
Rao, Dinesh Krishna.
Institution:
University of the South Pacific.
Award:
M.Sc.
Subject:
Date:
2006.
Call No.:
Pac QA 276 .6 .R36 2006
BRN:
1019058
Copyright:
40-60% of this thesis may be copied without the authors written permission
Abstract:
In this thesis,the limiting Gaussian distribution of a class of Cram´er-von Mises statistics{T N }for two-sample problem pertaining to empirical processes of the squared residuals from two independent samples of ARCH processes is elucidated. A distinctive feature is that, unlike the residuals of ARMA processes, the asymptotics{T N}depend on those of ARCH volatility estimators. Based on the asymptotis of{T N},we numerically assess the relative asymptotic efficiency and ARCH volatility effect for some ARCH residual distributions. Moreover, a measure of robustness for {T N }is introduced. Then this aspect of{T N}based on such residual distributions is illustrated numerically. In contrast with the i.i.d.or ARMA settings, these studies illuminate some interesting features of ARCH residuals.
|
|
|
