Evaluation of Information in Longitudinal Data

By Max Petzold
November 2003
Almqvist & Wiksell International
ISBN: 91-22-02019-5
95 pages, Illustrated, 6 " x 9 "
$47.50 Paper Original

This is a Ph.D. dissertation. Longitudinal analysis is important when individual effects are present. In this thesis some methods for different kinds of inference on longitudinal data are derived and evaluated in small sample settings. Appropriate evaluation criteria are determined from the actual inferential situation. It is based on three papers: "Maximum Likelihood Ratio Based Small-Sample Tests for Random Coefficients in Linear Regression", "Preliminary Testing in a Class of Simple Non-Linear Mixed Models to Improve Estimation Accuracy" and "Detection of Intra-Uterine Growth Restriction."


Return to Coronet Books main page