Pseudoreplication is a pseudoproblem
Publication Type: |
Journal Article |
Year of Publication: |
2009 |
Authors: |
Jeffrey C. Schank, Thomas J. Koehnle |
Publication/Journal: |
Journal of Comparative Psychology |
Keywords: |
experimental design, pseudoreplication, statistical analysis |
ISBN: |
1939-2087 0735-7036 |
Abstract:
Pseudoreplication is one of the most influential methodological issues in ecological and animal behavior research today. At its inception, the idea of pseudoreplication highlighted important concerns about the design and analysis of experiments in ecology. The doctrine purported to provide a unified view of experimental design and analysis, wherein precise criteria could be used to assess manuscripts and research proposals for acceptance or rejection. Few methodological doctrines have had as much impact as pseudoreplication, yet there has been very little critical analysis of it. In this paper, the authors extend the growing criticism of the concept of pseudoreplication. The authors argue that the core ideas behind pseudoreplication are based on a misunderstanding of statistical independence, the nature of control groups in science, and contexts of statistical inference. The authors also highlight how other areas of research have found and responded to similar issues in the design and analysis of experiments through the use of more advanced statistical methods. Ultimately, there are no universal criteria for accepting or rejecting experimental research; all research must be judged on its own merits.