New Randomized Response Technique for Estimating the Population Total of a Quantitative Variable

A new randomized response technique for estimating the population total, or mean of a quantitative variable is proposed. It provides high degree protection to respondents because they never report their data. Therefore, it may be favorably perceived by them and increase willingness cooperate. Instead revealing true value characteristic under investigation, respondent only states whether greater (or smaller) than number which selected him/her at random unknown interviewer. For each respondent, this number, sort individual threshold, generated as pseudorandom number. Furthermore, two modifications proposed are presented. The first modification assumes that interviewer also knows second deals with issue that, certain variables, such income, embarrassing either low values. Thus, depending on fixed threshold (unknown respondent), asked different questions avoid being embarrassed. suggested approach applied in detail simple sampling without replacement, but can be, after straightforward modification, many schemes, including cluster sampling, two-stage stratified sampling. results simulations illustrate behavior technique.