Quantifying the Information from a Randomized Response

by by Andrew A. Neath.

Abstract: Randomized response is a method designed for obtaining usable data on sensitive issues while protecting the privacy of those surveyed. Textbooks on introductory statistics, mathematical statistics, and sampling theory, among others, include examples of these techniques. But the impression that a randomized response completely hides sensitive information about the respondent is incorrect. In this paper, we look to analyze the information on a respondent divulged from such a survey.

Key Words: survey sampling, relative risk, Bayesian analysis

Andrew A. Neath, aneath@siue.edu

Editor: Richard G. Graf,rgraf@sunstroke.sdsu.edu

READING THE ARTICLE: You can read the article in portable document (.pdf) format (75080 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2276 times since July 24, 2006.

Return to the InterStat Home Page.