Estimation of Mean of a Sensitive Quantitative Variable in Complex Survey: Improved Estimator and Scrambled Randomized Response Model

Abstract

Highlights• This paper introduces a new Scrambled Randomized Response model. • A simulation study is done to compare the efficiency of the proposed model. • The results showed that the proposed model performs better than existing model. Article Info AbstractWith the intention to control a true swapping between the efficiency and the privacy protection this paper introduces a scrambled randomized response (SRR) model to be alternative of Saha's scrambling mechanism. The basic initiative is to provide an assortment of the additive, the subtractive and the multiplicative models. The simulation and the empirical studies are provided for various sample sizes to compare the efficiency of the proposed model. The results obtained from simulation showed that the proposed model performs better than Pollock and Bek's additive model. Also, the proposed generalized estimator of mean has been studied using a new SRR model presented in this article and shown that the proposed estimator and its class of estimators are more efficient than existing estimators. It is also shown that gain in efficiency is more when the proposed SRR model is used. The efficiency of the proposed class of estimators over existing estimators using both models is also provided using real data and with a simulation study.

Median estimation in the presence of non-response using randomised response technique

“…The regression-cum-ratio median estimator has been found to perform better than all other estimators mentioned in the research. This is supported by Mutembei et al (2014), who proposed a regression-cum-ratio estimator that uses data from multiple auxiliary variables and characteristics simultaneously to estimate the population mean (Koyuncu et al, 2019).…”