On the Bayesian Estimation of Synthesized Randomized Response Techniques for Obtaining Sensitive Information

The reduction of response bias in survey research is crucial ensuring that the collected data accurately represents the target population. In this study, the Bayesian Estimation of the Synthesized Random Response Technique (BESRRT) estimators are proposed as an effective method for minimizing response bias. The BESRRT estimators are being expressed using different priors, such as the Kumaraswamy, Generalized Beta, and Beta‐Nakagami distributions. The study employs numerical data investigation and preanalyzed data to compare the performance of the proposed estimators with other conventional models and assess the efficiency of the proposed technique. The results indicate that the BESRRT estimators, particularly the Beta‐Nakagami Distribution prior estimators, outperform other estimators and can potentially improve the accuracy of survey data for informed decision‐making. Consequently, the study concludes that the proposed method is more effective in reducing response bias in surveys involving sensitive information.