Compute scagnostics - scatterplot diagnostics

Calculates graph theoretic scagnostics. Scagnostics describe various measures of interest for pairs of variables, based on their appearance on a scatterplot. They are useful tool for discovering interesting or unusual scatterplots from a scatterplot matrix, without having to look at every individual plot.


NEWS/ChangeLog for scagnostics

0.2-4 2012-11-05 o fix a bug in normalizePoints() causing all-negative data to be scaled incorrectly

0.2-3 2009-01-27 o updated documentation, added examples

0.2-2 2008-12-22 o added scagnosticsOutliers() and scagnosticsExemplars()

0.2-1 2008-12-03 o initial version using original scagnostics Java code

0.1 [scagnostics 0.1 was a different package mainained by Hadley Wickham based on the same work of Wilkinson et al. In order to not confuse the two packages we didn't use version 0.1]

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.2-4.1 by Simon Urbanek, 2 years ago,

Browse source code at

Authors: Lee Wilkinson <[email protected]> and Anushka Anand

Documentation:   PDF Manual  

Task views: Graphic Displays & Dynamic Graphics & Graphic Devices & Visualization

file LICENSE license

Depends on rJava

Suggested by GGally, PairViz, condvis, condvis2, loon, zenplots.

See at CRAN