A forced optional randomized response model for estimating the proportion of sensitive attribute

The randomized response technique (RRT) is widely considered for estimating the sensitive attribute in sample surveys. Various randomized response methods have been formulated by the different researchers which provide suitable estimates and privacy protection to the respondents. In the present paper, a new randomized response technique is introduced for estimating a sensitive attribute by amalgamating forced answer strategy into optional RRT. The mean and variance of estimates of proportion of sensitive attribute and sensitivity level under proposed method are derived. The proposed procedure is found to be more efficient than the existing RRTs. The privacy of the respondents possessing the sensitive attribute is well protected under the proposed strategy. The superiority of the proposed procedure is established with the help of a numerical study.