15. ANCOVA for Dichotomous Dependent Variables

  1. Bradley E. Huitema

Published Online: 14 OCT 2011

DOI: 10.1002/9781118067475.ch15

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) ANCOVA for Dichotomous Dependent Variables, 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.ch15

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);
  • dichotomous dependent variables;
  • logistic model;
  • logistic regression;
  • multiple covariates

Summary

Logistic regression is recommended for estimating the parameters of a modified analysis of covariance (ANCOVA) model that is designed for dichotomous outcome variables. Dichotomous ANCOVA can be carried out using two regressions. First, the dichotomous outcome is regressed on all group membership dummy variables and all covariates using logistic regression. Second, the dichotomous outcome is regressed on covariates. The G-statistic from the second regression is subtracted from the G-statistic from the first regression to compute a chi-square statistic. This chi-square is used to test the hypothesis that the adjusted event probabilities are equal for all treatments. The methods shown in this chapter generalize to other analyses related to ANCOVA such as tests for homogeneous regression, picked points analysis, and quasi-ANCOVA.

Controlled Vocabulary Terms

analysis of covariance; logistic regression