Table 2 Univariate vs. multivariate analysis.

From: Recent innovations and in-depth aspects of post-genome wide association study (Post-GWAS) to understand the genetic basis of complex phenotypes

Univariate approaches

Multivariate approaches

Analyzing each phenotype separately, Showing independent phenotype changes

Availability of subject-level data

Tests to compare different set of samples, combining results to compare, Correlation procedure is needed

measuring two or more variables for each subject, dealing with simultaneous relationship among variables

Using variable mean

Using mean in addition to covariances or correlations

Needs multiple significant tests

Requires genotype and phenotype information

Ease of application, Ease of interpretation, Ease of communication of the results

Improve statistical power of association signals

Proving complementary results to multivariate analysis

Providing complementary results to univariate analysis

  1. Some properties include the advantages and disadvantages of using univariate and multivariate approaches (Saccenti et al., 2014).
Back to article page