Respondent privacy and estimation efficiency in randomized response surveys for discrete-valued sensitive variables

TL;DR

This paper develops a randomized response method for surveys on discrete-valued sensitive variables, balancing respondent privacy with estimation efficiency, and extends the approach to polychotomous populations.

Contribution

It introduces a new randomization device and estimation procedure for discrete variables, enhancing privacy protection while maximizing efficiency.

Findings

Proposed a novel randomization device for discrete variables

Derived an estimation method that balances privacy and efficiency

Extended results to polychotomous populations

Abstract

In some socio-economic surveys, data are collected on sensitive or stigmatizing issues such as tax evasion, criminal conviction, drug use, etc. In such surveys, direct questioning of respondents is not of much use and the randomized response technique is used instead. A few researchers have studied the issue of privacy protection or respondent jeopardy for surveys on dichotomous populations, where the objective is to estimate the proportion of persons bearing the sensitive trait. However, not much is yet known about respondent protection when the variable under study takes discrete numerical values and the objective of the survey is to estimate the population mean of this variable. In this article we study this issue. We first propose a randomization device for this situation and give the corresponding estimation procedure. We next propose a measure of privacy and show that given a certain stipulated level of this privacy measure, we can determine the parameter of the randomization device so as to maximize the efficiency of estimation, while guaranteeing the desired level of privacy protection. In particular, our study also covers the case of polychotomous populations and we can estimate the proportions of individuals belonging to the different classes. Consequently, results for dichotomous populations follow as corollaries.