Pairwise Display of High-Dimensional Information via Eulerian Tours and Hamiltonian Decompositions

A graph theoretic approach is taken to the component order problem in the layout statistical graphics. Eulerian tours and Hamiltonian decompositions of complete are used to ameliorate order effects in statistical graphics. Similar traversals of weighted graphs are used to amplify the visual effect of selected salient features the data. Relevant graph theory is summarized and classic algorithms are tailored this problem. Graphics for multiple comparisons are reviewed and a new display that is based on graph traversal. Improved star glyph displays of multivariate are described. Parallel coordinate displays tailored to particular features of the are developed. The methods and new graphical displays are made available as an package, PairViz.