FRIDAY, June 13, 2003
Time: 2:00 - 3:00 PM
Constant Hall Room 1008

Title: Estimation of Parameters in Replicated Time Series Regression Models

Mr. Genming Shi
Department of Mathematics and Statistics, Old Dominion University

The time series regression model was widely studied in the literature by several authors. However, statistical analysis of replicated time series regression models has received little attention. In this thesis, we study the application of quasi-least squares, a relatively new method, to estimate the parameters in replicated time series models with general ARMA(p, q) correlation structure. We also study several established methods for estimating the parameters in those models, including the maximum likelihood, method of moments, and the GEE method. Asymptotic comparisons of the methods are made by fixing the number of repeated measurements in each series, and letting the number of replications n go to infinity. Our theoretical as well as some simulations results show that the quasi-least squares estimates are undoubtedly better than the moment estimates, and are good competitors and more robust than the maximum likelihood estimates.