enEnglish
CROS

Indirect identification

Document date: 
Wednesday, 8 May, 2019
Language: 
English

Indirect identification

DEFINITION:
Indirect identification is inferring the identity of a population unit within a microdata release other than from direct identification.

SOURCES:

Primary source: CODED-Statistical methodologies

Secondary sources: NIST, CODED-EU legislation

INTERPRETATION:

Contrary to direct identification of a Statistical unit from its formal Identifiers, Indirect identification uses combined information elements to identify specific units. The Variables which are combined are called “Indirect identifiers”. Examples of “Indirect identifiers” are place of birth, race, religion, weight, activities, employment information, medical information, education information, and financial information.

CONTEXT:

The integration of different Administrative sources adds indirect Identifiers to a dataset and increases the risk of Indirect identification of Statistical units. This can violate privacy regulations for Statistical data.

ADDITIONAL INFORMATION:

Methods of statistical disclosure control can help to prevent the risk of Indirect identification.

RELATED TERMS:

Anonymization, Data hashing, Disclosive cell, Personal data, Pseudonymisation, Re-identification, Statistical unit

 Cross-linked glossary TOP