It is essential that the scientific community develop and deploy accurate and high-throughput techniques to capture factors that influence plant phenotypes if we are to meet the projected demands for food and energy. In recognition of this fact, multiple research institutions have invested in automated high-throughput plant phenotyping (HTPP) systems designed for use in controlled environments. These systems can generate large amounts of data in relatively short periods of time, potentially allowing researchers to gain insights about phenotypic responses to environmental, biological, and management factors. Reliable inferences about these factors depends on the use of proper experimental design when planning phenotypic studies in order to avoid issues such as lack of power and confounding. In this chapter, the topic of experimental design will be discussed, from basic principles to examples specific to controlled environment plant phenotyping. Examples will be provided based on the package agricolae in the R statistical language.