Affiliation:
1. Melbourne School of Psychological Sciences University of Melbourne Parkville Victoria Australia
2. Department of Psychology McGill University Montreal Quebec Canada
3. Oxford Internet Institute University of Oxford Oxford UK
4. Wilhelm Wundt Institute for Psychology Leipzig University Leipzig Germany
5. Department of Operations, Information, and Decisions The Wharton School University of Pennsylvania Philadelphia Pennsylvania USA
Abstract
AbstractThe replication crisis and subsequent credibility revolution in psychology have highlighted many suboptimal research practices such as p‐hacking, overgeneralizing, and a lack of transparency. These practices may have been employed reflexively but upon reflection, they are hard to defend. We suggest that current practices for reporting and discussing study limitations are another example of an area where there is much room for improvement. In this article, we call for more rigorous reporting of study limitations in social and personality psychology articles, and we offer advice for how to do this. We recommend that authors consider what the best argument is against their conclusions (which we call the “steel‐person principle”). We consider limitations as threats to construct, internal, external, and statistical conclusion validity (Shadish et al., 2002), and offer some examples for better practice reporting of common study limitations. Our advice has its own limitations — both our representation of current practices and our recommendations are largely based on our own metaresearch and opinions. Nevertheless, we hope that we can prompt researchers to write more deeply and clearly about the limitations of their research, and to hold each other to higher standards when reviewing each other's work.