7. Analysis of Covariance through Linear Regression

  1. Bradley E. Huitema

Published Online: 14 OCT 2011

DOI: 10.1002/9781118067475.ch7

The Analysis of Covariance and Alternatives: Statistical Methods for Experiments, Quasi-Experiments, and Single-Case Studies, Second Edition

The Analysis of Covariance and Alternatives: Statistical Methods for Experiments, Quasi-Experiments, and Single-Case Studies, Second Edition

How to Cite

Huitema, B. E. (2011) Analysis of Covariance through Linear Regression, in The Analysis of Covariance and Alternatives: Statistical Methods for Experiments, Quasi-Experiments, and Single-Case Studies, Second Edition, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/9781118067475.ch7

Author Information

  1. Department of Psychology, Western Michigan University, Kalamazoo, Michigan, USA

Publication History

  1. Published Online: 14 OCT 2011
  2. Published Print: 14 OCT 2011

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: 9780471748960

Online ISBN: 9781118067475

SEARCH

Keywords:

  • analysis of covariance (ANCOVA);
  • analysis of variance (ANOVA);
  • computation of adjusted means;
  • homogeneity of regression;
  • multiple linear regression;
  • partial correlation methods

Summary

Simple (one-way) analysis of variance problems can be computed through regression analysis by regressing the dependent variable scores (Y) on so-called dummy variable (s). Once the regression approach to analysis of variance (ANOVA) problems is mastered, the analysis of covariance (ANCOVA) can be easily conceptualized as a slight extension of the same ideas. Multiple regression software can be conveniently employed to carry out the analysis of covariance and the homogeneity of regression slope tests, if dedicated routines for ANCOVA model are not available. The homogeneity of regression slopes test can also be computed using regression. This involves the regression of the dependent variable on the dummy variables, the covariate, and the products of the dummy variables and the covariate.

Controlled Vocabulary Terms

Multiple regression