Simultaneous prediction intervals for multiple steps ahead forecasts in vector time series.

Yick, Kwok Leung.Thesis (M.Phil.)--Chinese University of Hong Kong, 2007.Includes bibliographical references (leaves 67-68).Abstracts in English and Chinese.Chapter 1 --- Introduction --- p.1Chapter 1.1 --- The importance of forecasting --- p.1Chapter 1.2 --- Objective --- p.3Chapter 2 --- Vector Autoregressive Model --- p.5Chapter 2.1 --- The VAR(p) model --- p.5Chapter 2.2 --- Least squares estimation method --- p.7Chapter 2.3 --- VAR order selection method --- p.10Chapter 2.4 --- Constructing simultaneous prediction intervals procedures --- p.11Chapter 2.4.1 --- Bonferroni procedure --- p.12Chapter 2.4.2 --- The 'Exact' procedure --- p.13Chapter 2.4.3 --- Two variables case --- p.15Chapter 2.4.4 --- Three variables case --- p.18Chapter 3 --- A System of Linear Equations with Exogenous Variables --- p.23Chapter 3.1 --- Restriction of VAR model --- p.23Chapter 3.2 --- Least squares estimation method --- p.24Chapter 3.3 --- Hsiao's sequential method for estimating the lag lengths --- p.26Chapter 3.3.1 --- Two variables case --- p.27Chapter 3.3.2 --- Three variables case --- p.29Chapter 3.4 --- Using VAR model to construct simultaneous prediction intervals --- p.32Chapter 3.4.1 --- Bonferroni procedure --- p.34Chapter 3.4.2 --- The 'Exact' procedure --- p.35Chapter 3.4.3 --- Two variables case --- p.36Chapter 3.4.4 --- Three variables case --- p.38Chapter 4 --- Illustrative Examples --- p.42Chapter 5 --- A Simulation Study --- p.52Chapter 5.1 --- Design of the experiment --- p.52Chapter 5.2 --- Simulation results --- p.58Chapter 5.3 --- Concluding remarks --- p.60Chapter 5.4 --- Further research --- p.60References --- p.6