When collecting data from people, it is always best to minimise the amount of personal data you collect from your participants. If possible, you should not collect directly identifiable information unless it is required to answer your research question. This helps protect the privacy of your participants and decreased the likelihood of re-identification.
If personal data must be collected, it should be de-identified as much as possible. Two terms which are used to describe de-identification are anonymous and pseudonymous. They do not mean the same thing.
Anonymous data means a participant can never be re-identified from the data contained in a dataset, even if the data is merged with another dataset. Full anonymity is very difficult and usually not achievable without removing all the 'useful' information that is good for research.
Examples of anonymous data:
Pseudonymous data means a participant can still be re-identified from the dataset. However, they cannot be identified without some additional information.
Techniques for pseudonymisation:
Below you will find a table which portrays the differences between terms.