Standard Article

Pairwise Independence

  1. Nanny Wermuth

Published Online: 15 JUL 2005

DOI: 10.1002/0470011815.b2a15113

Encyclopedia of Biostatistics

Encyclopedia of Biostatistics

How to Cite

Wermuth, N. 2005. Pairwise Independence. Encyclopedia of Biostatistics. 6.

Author Information

  1. Universität Mainz, Mainz, Germany

Publication History

  1. Published Online: 15 JUL 2005

Abstract

If two explanatory variables are independent, with additive effects on a third, response, variable, then the overall effect of one explanatory variable is qualitatively the same as the effect conditional on the other explanatory variable. If the explanatory variables are dependent, reversal can occur. In multivariate analysis, pairwise independence of all variables does not imply mutual independence.

Keywords:

  • additive model;
  • Simpson's paradox;
  • correspondence analysis;
  • explanatory