Estimation of mean in randomized response surveys when answers are incompletely truthful

Abstract

Privacy is an important issue in sensitive survey. In this paper,we propose a new quantitative randomized response procedure which considers incompletely truthful answers from respondents. The proposed strategy considers the aspect of privacy protection offered to the interviewees. Under simple random sampling with replacement(SRSWR) and the same size of a sample, efficiency comparisons are carried out to investigate the performance of the proposed method. Under a reasonable condition, the estimation obtained from the proposed method possesses smaller mean square error than estimation obtained using Jinying and Liangxiaojun [4]’s strategy.