• Journal of the Korean Data and Information Science Society
• /
• v.14 no.3
• /
• pp.489-499
• /
• 2003

In this paper we implement the system for the forced answer model which is an indirect response technique on the internet as a way of obtaining much more precise information, not revealing secrets of responsors. In this system we consider that respondents are generally reluctant to answer in a survey to get sensitive information targeting employees, customers, etc.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.311-318
• /
• 1993

In this paper, we consider the test based on using Forced question model instead of Warner model and compare the power of two randomized respose models. The estimator for the prportion of the individuals belonging to the sensitive group is obtained by using Forced question model and the conditions that the estimator by Forced question model will be more efficient than the estimators by Warner model are found when the respondents are truthrul in their answers.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.271-277
• /
• 2010

The randomized response technique is an indirect question that employs a randomizing device to protect respondents' privacy. The technique is now considered the most efficient of the newly developed techniques. In this technique, Chang et al. (2004) suggests an improved forced-answer technique and finds more efficient conditions than Warner did in 1965. But it is the weakness of the technique to lose more information than a direct response technique does. Therefore, a lot of researches have developed new techniques to reduce loss of information, to enhance estimated efficiency, and to efficiently use collected information. Considering this tendency, this paper also tries to improve Chang's technique. It suggests the technique that is extended from Chang's and finds more efficient conditions than Chang's technique and Mangat and Singh's (1990) did.