Sensitivity estimation for personal interview survey questions

Abstract

This paper proposes an optional RRT method to estimate the sensitivity level of personal interview survey questions with quantitative response. The method is similar to the one used by Gupta et al. (2002) but estimates both the average response level and the sensitivity level of the question. A numerical example explains the estimation process and a simulation study assesses the effectiveness of the proposed method. We also compare the performance of the proposed estimator with the “Full” and “Partial” randomized response models.