Brief Overview of the Augmented Design Approach
For those of you new to the concept of experimental design, there are various approaches to how a researcher can plan an experiment. In the context of an experiment in the domain of agronomy, let's say a researcher wants to test 10 different types of fertilizers. Questions such as where should the plots be located where the experiment will be conducted, how many replications should be made of each fertilizer type being tested, and which plot should be applied with which fertilizer, etc. all play an important role. One experimental approach, called Augmented Design was first introduced by Federer in 1956 (Federer, W.T. 1956. Augmented (or hoonuiaku) designs. Hawaiian Planters’ Record LV(2): 191–208).
In augmented designs the goal is to compare existing (control) treatments with new treatments that have an experimental constraint of "limited replication". To understand limited replication think about experiments that may only allow a single representation of the new treatment, this limitation may be many times due to the cost associated with the experiment, limited resources, or limited number of new units that can be used in the experiment. In contrast, the existing treatments are referred as checks and are generally replicated multiple times. With augmented design one can estimate the following:
a) Differences between checks and new treatments,
b) Differences among new treatments,
c) Differences among check treatments, and
d) Differences among new and check treatments combined.
Continuing with our simple agronomy example, a researcher may have a fertilizer type that is commonly used and regarded as the best on the market. The researcher will use this as a control treatment and compare it against 9 new types of fertilizers her/his company is developing for potential new commercial products. The challenge is the researcher has only limited field space and limited amounts of each fertilizer to conduct this experiment, so only one plot per new fertilizer can be planted, no replications. Therefore, the Augmented Design will be useful.
This eLesson requires that you have a general understanding of the augmented experimental design. If this concept is unclear to you or if you would like a quick refresher with more in depth descriptions, we would like you to review the two additional resources linked at the bottom of this page.
The first link is a webinar sponsored by the eXtension Plant Breeding and Genomics Community of Practice. In this archived webinar, Dr. Jennifer Kling of Oregon State University presents an Introduction to the Augmented Experimental Design. Although she demonstrates data analysis using the stats program, SAS, her explanation of the experimental approach will be useful for understanding augmented experimental design. In addition, we would like to take the time here to acknowledge that Dr. Kling has also graciously allowed us to use her data for our training in the eLesson for demonstrating the use of R tools.
The second link is a Journal Club site at Purdue which provides a nice collection of a research article, additional PowerPoint and data sets that go into further depth in describing the Augmented Design approach.
Augmented Experimental Design (Additional Resources)