Regression Cube: A Technique for Multidimensional Visual Exploration and Interactive Pattern Finding

While scatterplots are commonly used to visualize multidimensional data, 2D projections of data offer lim-ited understanding of the high dimensional interactions between data points. In this paper, we introduce an interactive 3D extension of scatterplots called the Regression Cube (RC), which augments a 3D scatter-plot with three facets on which the correlations between the two variables are revealed by sensitivity lines and sensitivity streamlines. The sensitivity visualization of local regression on the 2D projections provides insights about the shape of the data though its orientation and continuity cues. We also introduce a series of visual operations such as clustering, brushing, and selection supported in RC. By iteratively refining the selection of data points of interest, RC is able to reveal salient local correlation patterns that may other-wise remain hidden with a global analysis. We have demonstrated our system with two case studies and a user-oriented evaluation, and we show how RCs enable interactive visual exploration of multidimensional datasets via a variety of classification and information retrieval tasks. The video demo of RC is at [Chan et al. 2013c]