Don't let spurious accusations of pseudoreplication limit our ability to learn from natural experiments (and other messy kinds of ecological monitoring)

Abstract

Pseudoreplication is defined as the use of inferential statistics to test for treatment effects where treatments are not replicated and/or replicates are not statistically independent. It is a genuine but controversial issue in ecology particularly in the case of costly landscape-scale manipulations, behavioral studies where ethics or other concerns may limit sample sizes, ad hoc monitoring data, and the analysis of natural experiments where chance events occur at a single site. Here key publications on the topic are reviewed to illustrate the debate that exists about the conceptual validity of pseudoreplication. A survey of ecologists and case studies of experimental design and publication issues are used to explore the extent of the problem, ecologists' solutions, reviewers' attitudes, and the fate of submitted manuscripts. Scientists working across a range of ecological disciplines regularly come across the problem of pseudoreplication and build solutions into their designs and analyses. These include carefully defining hypotheses and the population of interest, acknowledging the limits of statistical inference and using statistical approaches including nesting and random effects. Many ecologists face considerable challenges getting their work published if accusations of pseudoreplication are made - even if the problem has been dealt with. Many reviewers reject papers for pseudoreplication, and this occurs more often if they haven't experienced the issue themselves. The concept of pseudoreplication is being applied too dogmatically and often leads to rejection during review. There is insufficient consideration of the associated philosophical issues and potential statistical solutions. By stopping the publication of ecological studies, reviewers are slowing the pace of ecological research and limiting the scope of management case studies, natural events studies, and valuable data available to form evidence-based solutions. Recommendations for fair and consistent treatment of pseudoreplication during writing and review are given for authors, reviewers, and editors.

Keywords: Bayesian statistics; P‐values; confounded effects; hypothesis formation; nesting; peer review; random effects; scientific publication; statistical population.

Figure 1

Hypothetical example of two experimental designs examining the effects of some form of disturbance (e.g., wildfire, grazing) on vegetation structure at two different elevations. Design A is a formal experiment, whereas Design B is a researcher's response to a natural (i.e., unplanned by the researcher) event. Dotted lines mark the perimeter of the disturbances which could be, for example, a series of experimental fires in A and a wildfire in B or a number of grazing exclosures in A vs. a landscape‐scale fence in B. Assuming that soils, slope, and aspect are more or less homogenous, at least within each studied elevational band, are the results of Design A more ecologically meaningful than those in B? Which design more adequately captures the ecological reality of wildfire or landscape‐scale alterations to grazing management? We would argue that Design A might actually sacrifice ecological reality for statistical independence as, for example, small fires cannot mimic a wildfire event and small grazing exclosures do not allow natural movement of grazers across landscapes.