This article uses the framework of Ioannidis (2005) to organise a discussion of issues related to the ‘reproducibility crisis’. It then goes on to use that framework to evaluate various proposals to fix the problem. Of particular interest is the ‘post‐study probability’, the probability that a reported research finding represents a true relationship. This probability is inherently unknowable. However, a number of insightful results emerge if we are willing to make some conjectures about reasonable parameter values. Among other things, this analysis demonstrates the important role that replication can play in improving the signal value of empirical research.
The reproducibility crisis, that is, the fact that many scientific results are difficult to replicate, pointing to their unreliability or falsehood, is a hot topic in the recent scientific literature, and statistical methodologies, testing procedures and p‐values, in particular, are at the centre of the debate. Assessment of the extent of the problem–the reproducibility rate or the false discovery rate–and the role of contributing factors are still an open problem. Replication experiments, that is, systematic replications of existing results, may offer relevant information on these issues. We propose a statistical model to deal with such information, in particular to estimate the reproducibility rate and the effect of some study characteristics on its reliability. We analyse data from a recent replication experiment in psychology finding a reproducibility rate broadly coherent with other assessments from the same experiment. Our results also confirm the expected role of some contributing factor (unexpectedness of the result and room for bias) while they suggest that the similarity between original study and the replica is not so relevant, thus mitigating some criticism directed to replication experiments.
Most scientific papers are not reproducible: it is really hard, if not impossible, to understand how results are derived from data, and being able to regenerate them in the future (even by the same researchers). However, traceability and reproducibility of results are indispensable elements of highquality science, and an increasing requirement of many journals and funding sources. Reproducible studies include code able to regenerate results from the original data. This practice not only provides a perfect record of the whole analysis but also reduces the probability of errors and facilitates code reuse, thus accelerating scientific progress. But doing reproducible science also brings many benefits to the individual researcher, including saving time and effort, improved collaborations, and higher quality and impact of final publications. In this article we introduce reproducible science, why it is important, and how we can improve the reproducibility of our work. We introduce principles and tools for data management, analysis, version control, and software management that help us achieve reproducible workflows in the context of ecology.
When computational experiments include only datasets, they could be shared through the Uniform Resource Identifiers (URIs) or Digital Object Identifiers (DOIs) which point to these resources. However, experiments seldom include only datasets, but most often also include software, execution results, provenance, and other associated documentation. The Research Object has recently emerged as a comprehensive and systematic method for aggregation and identification of diverse elements of computational experiments. While an entire Research Object may be citable using a URI or a DOI, it is often desirable to cite specific sub-components of a research object to help identify, authorize, date, and retrieve the published sub-components of these objects. In this paper, we present an approach to automatically generate citations for sub-components of research objects by using the object’s recorded provenance traces. The generated citations can be used "as is" or taken as suggestions that can be grouped and combined to produce higher level citations.
Bibliographic databases provide access to scientific literature through targeted queries. The most common uses of these services, aside from accessing scientific literature for personal use, are to find relevant citations for formal surveys of scientific literature, such as systematic reviews or meta-analysis, or to estimate the number of publications on a certain topic as a measure of sampling effort. Bibliographic search tools vary in the level of access to the scientific literature they allow. For instance, Google Scholar is a bibliographic search engine which allows users to find (but not necessarily access) scientific literature for no charge, whereas other services, such as Web of Science, are subscription based, allowing access to full texts of academic works at costs that can exceed $100,000 annually for large universities (Goodman 2005). One of the most commonly used bibliographic databases, Clarivate Analytics–produced Web of Science, offers tailored subscriptions to their citation indexing service. This flexibility allows subscriptions and resulting access to be tailored to the needs of researchers at the institution (Goodwin 2014). However, there are issues created by this differential access, which we discuss further below.
On 24 May 2018, Maria Cruz, Shalini Kurapati, and Yasemin Türkyilmaz-van der Velden led a workshop titled “Software Reproducibility: How to put it into practice?”, as part of the event Towards cultural change in data management - data stewardship in practice held at TU Delft, the Netherlands. There were 17 workshop participants, including researchers, data stewards, and research software engineers. Here we describe the rationale of the workshop, what happened on the day, key discussions and insights, and suggested next steps.