A0723
Title: Estimation parameter for two-stage randomized response technique in logistic regression model
Authors: Kim Hung Pho - Feng Chia University (Taiwan) [presenting]
Abstract: When a survey study is related to sensitive issues, such as political orientation, sexual orientation, and income, interviewee may not be willing to respond truthfully, which leads to bias results. In order to protect the interviewee privacies and improve their willingness to provide the correct answer, the randomized response (RR) technique has been proposed, in which the respondents randomly selects questions by means of devices in order to ensure that they are protected. This design has been extended to propose a two-stage RR design. Not only can this method be used to estimate the proportion of a sensitive group, but also to estimate the honest answer rate. We use the two-stage randomized response design to apply a logistic regression model to investigate and estimate the effects of covariates on the proportion of a sensitive feature and the honest response rate. As an application, the proposed methodology is applied to analyze the survey data of sexuality of freshmen at Feng Chia University in 2016.
