Estimation of stigmatized population total: A new additive quantitative randomized response model

Abstract

In this article, we propose a new randomized response model to estimate the population total of a sensitive variable of quantitative nature. The objective is achieved by introducing additive scrambling mechanism when sample is drawn through probability proportional to size sampling scheme. The performance evaluation of the proposed model is carried with respect to notable model of Odumade and Singh (2010). To maintain the generality, we consider variety of settings of design parameters. Furthermore, log-log model approach is employed to assess the predictive effects of design parameters over the percentage relative efficiency of the proposed scheme. The gain of using proposed method over contemporary model is documented throughout the article.