Chapter EIGHT. Principles in Dealing with Correlated Data
Published Online: 11 AUG 2003
DOI: 10.1002/0471467979.ch8
Copyright © 2003 John Wiley & Sons, Inc.
Book Title
Quantitative Methods in Population Health: Extensions of Ordinary Regression
Additional Information
How to Cite
Palta, M. (2003) Principles in Dealing with Correlated Data, in Quantitative Methods in Population Health: Extensions of Ordinary Regression, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/0471467979.ch8
Publication History
- Published Online: 11 AUG 2003
- Published Print: 15 AUG 2003
Book Series:
Book Series Editors:
- Walter A. Shewhart,
- Samuel S. Wilks
ISBN Information
Print ISBN: 9780471455059
Online ISBN: 9780471467977
- Summary
- Chapter
Keywords:
- correlated data;
- longitudinal data;
- spectral theorem;
- compound symmetry;
- unstructured covariance;
- block diagonal;
- empirical variance;
- principal components;
- information criterion;
- REPEATED statement
Summary
We provide examples of situations with correlated data. Unbiasedness of ordinary least squares estimators. Block diagonal variance matrices and how block diagonality simplifies matrix operations. Empirical variance with block diagonal structure. The spectral theorem and its application to correlated data and in principal components analysis. Different correlation structures are introduced. Applying correlation structures in analyses with PROC MIXED are shown and criteria discussed for choosing the best model.
Multivariate normal distribution. Maximum likelihood analysis of correlated data. Analysis of longitudinal blood pressure data with different assumptions on the correlation structure.