Laura Arns' thesis page

Synopsis
Often, statistical data samples consist of sample sets measured on more than two variables. For example, a data set may consist of water samples, chlorine, ammonia, phosphorus, and other pollutants. Such data is called high-dimensional or multivariate.

Many approaches have been used to visualize this type of data. Along with traditional static sorts of displays such as histograms, scatterplots, Chernoff faces, and parallel coordinate plots, most software provides interactive and dynamic querying of data. Currently , workstation-based tools such as XGobi are used to view multivariate data. These tools display 3D graphics on a traditional computer monitor. However, virtual reality devices offer the capability to display graphics in stereoscopic 3D, allowing the user to better perceive depth information. To date, there has been little virtual reality research in statistical graphics. The experiment persented here was designed to determine if there are advantages to a virtual reality environment for visualizing high-dimensional data.

People Involved
Dr. Carolina Cruz-Neira
Laura Arns