Dr. Tyler Morgan-Wall is a Research Staff Member at the Institute for Defense Analyses, and is the developer of the software library skpr: a package developed at IDA for optimal design generation and power evaluation in R. He is also the author of several other R packages for data visualization, mapping, and cartography. He has a PhD in Physics from Johns Hopkins University and lives in Silver Spring, MD.


The Department of Defense requires rigorous testing to support the evaluation of effectiveness and suitability of oversight acquisition programs. These tests are performed in a resource constrained environment and must be carefully designed to efficiently use those resources. The field of Design of Experiments (DOE) provides methods for testers to generate optimal experimental designs taking these constraints into account, and computational tools in DOE can support this process by enabling analysts to create designs tailored specifically for their test program. In this tutorial, I will show how you can run these types of analyses using “skpr”: a free and open source R package developed by researchers at IDA for generating and evaluating optimal experimental designs. This software package allows you to perform DOE analyses entirely in code; rather than using a graphical user interface to generate and evaluate individual designs one-by-one, this tutorial will demonstrate how an analyst can use “skpr” to automate the creation of a variety of different designs using a short and simple R script. Attendees will learn the basics of using the R programming language and how to generate, save, and share their designs. Additionally, “skpr” provides a straightforward interface to calculate statistical power. Attendees will learn how to use built-in parametric and Monte Carlo power evaluation functions to compute power for a variety of models and responses, including linear models, split-plot designs, blocked designs, generalized linear models (including logistic regression), and survival models. Finally, I will demonstrate how you can conduct an end-to-end DOE analysis entirely in R, showing how to generate power versus sample size plots and other design diagnostics to help you design an experiment that meets your program’s needs.