mu-comparison with many groups

[dylanbeaudette]

When summarizing more than 10 groups (e.g. an entire SSA) the graphical summaries of marginal distributions aren't feasible. It would be handy to graphically depict group-wise similarity via median values of each continuous variable, and maybe even factor variables via Gower's distance metric.

Something like this:

Groups could be evaluated according to one / more of:

• manual generalization of legend
• unsupervised classification
• tabular data summaries from component / muaggatt data

Output may be cluttered, so a more advanced labeling engine will be required. Also, searchable output would make the figure more far more useful. Consider SVG or {plotly} output devices.