**Analysis of Variance (ANOVA)**: An
analysis of the relative contributions of explained and unexplained sources of
variance in a continuous response variable. Here we use the term 'ANOVA' in its
broad sense to include explanatory factors that vary on continuous as well as categorical
scales. In its narrower sense, ANOVA refers to balanced designs
with categorical factors, while General Linear Models (GLM)
encompass also unbalanced designs and covariates.
Parametric ANOVA and GLM partition the total variance in the response by measuring sums of
squared deviations from modelled values. Significant effects are tested with
the *F* statistic, which assumes random
sampling of independent replicates, homogeneous within-sample variances, and a
normal distribution of the residual error variation around sample means.

Doncaster, C. P. & Davey, A. J. H. (2007) *Analysis of Variance and Covariance: How to
Choose and Construct Models for the Life Sciences*. Cambridge: Cambridge
University Press.

http://www.southampton.ac.uk/~cpd/anovas/datasets/