A Method for Generating Simulated Plasmodes and Artificial Test Clusters with User-Defined Shape, Size, and Orientation.

We present a simple method for generating simulated plasmodes and artificial test clusters with user-defined shape, size, and orientation. Our method differs from other cluster generation techniques in that it focuses on the validity of the cluster indicators. For J clusters, indicator validity is defined as the squared correlation ratio between the cluster indicator (i.e., the observed variable) and J-1 dummy variables. The within-cluster correlation structure and the univariate distributions of the cluster indicators are specified with procedures outlined by Fleishman (1978) and Vale and Maurelli (1983). Simulation results illustrate the utility of the method for cluster analysis evaluation research.