Weisberg and Cook will explore the use of real time, computationally intensive, graphical methods in statistics. The primary focus of this work shall be on developing new diagnostic tools for use in building statistical models and on the use of high quality graphical workstations for constructing likelihood- based confidence regions in nonlinear and generalized linear regression. Data spinning, multiple plots, and animation are the principal graphical tools to be used. Methods for augmenting plots of fitted models with real time computation of confidence bands will be explored. This research is in the general field of parametric statistical modeling, especially in regression. The work aims to create noveal approaches to assessing statistical models that take advantage of modern computational and graphical capabilities. It is expected that this work will have a significant impact on the analytical process used throughout the scientific community, since regression is one of the most widely use statistical techniques.
