NINE. A Further Study of How the Transformation Works with Correlated Data

  1. Mari Palta

Published Online: 11 AUG 2003

DOI: 10.1002/0471467979.ch9

Quantitative Methods in Population Health: Extensions of Ordinary Regression

Quantitative Methods in Population Health: Extensions of Ordinary Regression

How to Cite

Palta, M. (2003) A Further Study of How the Transformation Works with Correlated Data, in Quantitative Methods in Population Health: Extensions of Ordinary Regression, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/0471467979.ch9

Author Information

  1. Madison, Wisconsin, USA

Publication History

  1. Published Online: 11 AUG 2003
  2. Published Print: 15 AUG 2003

Book Series:

  1. Wiley Series in Probability and Statistics

Book Series Editors:

  1. Walter A. Shewhart and
  2. Samuel S. Wilks

ISBN Information

Print ISBN: 9780471455059

Online ISBN: 9780471467977

SEARCH

Keywords:

  • spectral theorem;
  • between individual effects;
  • within individual effects;
  • Balestra–Nerlove estimator;
  • lack of model fit;
  • cohort effect;
  • period effect;
  • confounding;
  • omitted covariate;
  • goodness of fit test

Summary

We apply the spectral theorem to two observations per cluster (individual). Decomposition into within and between individual effects, and highlighting of assumption that they are the same in Chapter 8 analyses. The Balestra–Nerlove formula for the compound symmetry estimator. Discussion of how the combined estimator weights within and between individual components. Practical reasons for why within and between individual affects may differ are listed. Cohort and period effects are discussed. Literature on the topic from econometrics and from biostatistics is referenced. Recommendations for how to proceed in practice to detect violation of the assumption on equality of within and between individual effects. Longitudinal blood pressure data are reanalyzed and a difference in between and within individual effects is detected. This is conjectured to be due to subjects starting blood pressure medication.