MANUAL CONTROLS FOR HIGH-DIMENSIONAL DATA PROJECTIONS

Projections of high-dimensional data onto low-dimensional subspaces pr ovide insightful views for understanding multivariate relationships. T his article discusses how to manually control the variable contributio ns to the projection. The user has control of the way a particular var iable contributes to the viewed projection and can interactively adjus t the variable's contribution. These manual controls complement the au tomatic views provided by a grand tour, or a guided tour, and give gre atly improved flexibility to data analysts.