Standard Article

Disease-Marker Association

  1. D. Schaid

Published Online: 15 JUL 2005

DOI: 10.1002/0470011815.b2a05016

Encyclopedia of Biostatistics

Encyclopedia of Biostatistics

How to Cite

Schaid, D. 2005. Disease-Marker Association. Encyclopedia of Biostatistics. 2.

Author Information

  1. Mayo Clinic, Rochester, MN, USA

Publication History

  1. Published Online: 15 JUL 2005

Abstract

Disease–marker association can be due to both genetic and nongenetic causes. The former are either that the marker plays a functional role in the disease process or that it is in close proximity to a disease locus (in linkage disequilibrium with it). Association can also be due to population stratification or admixture. Usual contingency table chi-square methods assume independence of alleles and/or individuals. In the absence of this independence, it is possible to allow for population heterogeneity by using genomic control (i.e. markers that are unlinked to the disease) or family-member controls, which provide various degrees of matching on ethnicity. Association studies can also use extended pedigree data provided that allowance is made for the statistical dependence of the members in the same pedigree.

Keywords:

  • attributable risks;
  • bias;
  • case–control studies;
  • confounding;
  • Hardy–Weinberg equilibrium;
  • McNemar statistic;
  • odds ratio