If you use a dataset compiled by another author or producer, you should cite (reference) the dataset just like you would cite any other information.
Citing a dataset:
- Ensures scientific transparency
- Provides credit for data creators, authors and data stewards
- Demonstrates the impact of researchers' work and establishes research data as an important contribution to the scholarly record
- Helps data authors verify how their data are being used
- Encourages the reuse of data for new research questions
- Creates a bibliographic "trail", connecting publications and supporting data, and establishing a timeline of publication and usage
How to cite?
Use the citation (reference) style specified by your publisher.
If no style is specified, include at least:
- Author or authors of dataset. Surname followed by first initials
- Publication year (or year range where relevant)
- Title of dataset
- Version
- Publisher
- DOI or URL
- Date accessed, when appropriate for a specific reference style
Example of dataset according to APA (7th ed.) reference style:
Paris, T., Kim, J., & Davis, C. (2015). EEG responses to two contexts of AV speech presentation [Data set]. Western Sydney University. http://doi.org/10.4225/35/54bf146fa4012
Example of dataset according to Harvard reference style:
Paris, T., Kim, J. & Davis, C. 2015. EEG responses to two contexts of AV speech presentation [Data set]. Western Sydney University. http://doi.org/10.4225/35/54bf146fa4012
The following source provide valuable guidelines:
Ball, A. & Duke, M. (2015). ‘How to Cite Datasets and Link to Publications’. DCC How-to Guides. Edinburgh: Digital Curation Centre.
https://www.dcc.ac.uk/sites/default/files/documents/publications/reports/guides/How_to_Cite_Link.pdf