A novel bivariate randomized response model using non-sensitive innocuous variable
摘要
Collection of data on simultaneous prevalence of two or more sensitive characteristics is a requirement in various research studies. In this paper, we introduce a two-stage Bivariate Randomized Response Model designed for this purpose, employing a design matrix based on a non-sensitive, unrelated characteristic. The application of the proposed model has been demonstrated via simulation study on real data sets. Additionally, an empirical study has been conducted to compare its efficiency with a standard method. The promising results led to recommendations for practical applications by survey statisticians and practitioners.