Understanding data confidentiality

Organisations have different requirements for protecting data confidentiality, privacy, and security so people, households, and organisations can’t be identified without their permission.

A data confidentiality report looking at best practice principles, and methodology-related content, has been produced by Stats NZ.

Data confidentiality report 

It's aimed at technical experts and managers - who supply and use data in New Zealand - to implement, evaluate, and verify techniques for protecting confidentiality.

Supporting images include the Degrees of identification in data diagram illustrating how data is on a spectrum with multiple shades of identifiability, while the Random rounding diagram looks at protecting information in counts tables.

Degrees of identification in data

Random rounding

Why confidentialise data?

Good data helps New Zealand grow and prosper. For planning, research, and information purposes, data must be high-quality, timely, and accurate.

When data is confidential it means no individuals, households, or businesses can be identified.

The report details the various methods available for confidentialising data, and outlines how understanding confidentiality principles, rules, and methods ensures we:

• don't release data that could identify people, households, or organisations unintentionally
• protect data provided by people and organisations, and ensure it isn't disclosed to anyone who isn't authorised to access it
• use statistical methods to prevent data from being disclosed in a way that could identify a person, household, or organisation unintentionally.

Key areas examined

• The principles, laws, and ethics governing data confidentiality.
• The methods used to keep data confidential.
• How perturbation (adding random noise to data) can be used to protect confidentiality.
• How aggregation (grouping categories together) can be used to protect confidentiality.
• How suppression (not releasing selected data) can be used to protect confidentiality.
• How limiting access (imposing strict limitations on access) to data can be used to protect confidentiality.
• How to build synthetic and confidential unit records to support the general publication of microdata.

Understanding different terms

The report explains the differences between terms - such as privacy, security, and confidentiality - that are often used interchangeably but have different meaning.

• Privacy ­– refers to a person’s ability to control the availability of data about themselves.
• Security – refers to how an organisation stores and controls access to the data it holds.
• Confidentiality – refers to the protection of data from, and about, individuals and organisations; and how we ensure that data is not made available or disclosed without authorisation.

Contact us

If you’d like more information, have a question, or want to provide feedback, email datalead@stats.govt.nz.