| Summary: | 碩士 === 銘傳大學 === 應用統計資訊學系碩士班 === 100 === Generally speaking, in the process of investigation, when the inquiry subjects are sensitive question, the respondents usually dishonest or refused to answer to protect personal privacy. These cases will make the error of statistical inference, and cause statistical data of sensitive issues often plate out of true. Warner(1965) first proposed “Randomized Response Model”, he hoped improved uncooperative situation by executing this model, and then get more reliable information to derive the proportion of sensitive groups. After that, many scholars also proposed other models to improve Warner(1965) model. For example, Greenberg et al.(1969) proposed “Unrelated-Question Model”, to improve the two questions which have the sensitive anxiety in Warner(1965) model; Christofides(2003) proposed generalized randomized response, use the "digital" instead of “yes” and ”no” to reduces the sensitive of the participant; Huang(2004) proposed “Two-Stage Random Response Model”, which combines direct response model with Warner(1965) model, it not only to estimate the proportion of sensitivity groups can also be estimated honest response rate.
In this article, we proposed an alternative model which combines Huang(2004) model and Wang and Tsai(2007) model and wishes supply enough protection to the respondents. And we can estimate the proportion of sensitive group more precisely with other models.
|
|---|
