Flexible Graphical Assessment of Experimental Designs in R: The vdg Package

• Main Authors: Pieter Schoonees, Niël le Roux, Roelof Coetzer
• Format: Article
• Language: English
• Published: Foundation for Open Access Statistics 2016-10-01
• Series: Journal of Statistical Software
• Subjects: experimental design; fraction of design space plot; variance dispersion graph; scaled prediction variance
• Online Access: https://www.jstatsoft.org/index.php/jss/article/view/2889

The R package vdg provides a flexible interface for producing various graphical summaries of the prediction variance associated with specific linear model specifications and experimental designs. These methods include variance dispersion graphs, fraction of design space plots and quantile plots which can assist in choosing between a catalogue of candidate experimental designs. Instead of restrictive optimization methods used in traditional software to explore design regions, vdg utilizes sampling methods to introduce more flexibility. The package takes advantage of R's modern graphical abilities via ggplot2 (Wickham 2009), adds facilities for using a variety of distance methods, allows for more flexible model specifications and incorporates quantile regressions to help with model comparison.