Let's suppose I have an ANOVA with three variables: Y ~ a + b + c. When I report the results, I would like to include the eta-squared for each of the three variables as a barplot.

My question is the following: since the definition of eta-squared is "the proportion of the total variability in the dependent variable that is accounted for by variation in the independent variable", could I also include a bar with the proportion of residual variability in the same plot? Although it is not

*technically*eta-squared, I think it would make sense to include it as a reference. Would that be inappropriate?

Many thanks!