The Challenge of Microdata Dissemination. A Methodology for a Public Use File Version of the WHIP Database
摘要
This study proposes a methodology for creating a Public Use File version of the WHIP database. The study aims to implement statistical methods to estimate the risk of identifying a subject belonging to the sample. The 3-step methodology starts with a mock interview of a subsample of the data, proceeds with the estimation of the identification risk, and applies standard anonymization methods, such as global recoding and local suppression, to the units at risk of re-identification.