Abstract:
|
A review of the randomized response model introduced by Warner (1965) is given, then a new randomized response model applicable to continuous data that considers a mixture of two normal distributions is introduced and analyzed in a parallel assessment to the work provided by McDonald (1994). This article provides a study of the efficiency, an estimation of some unknown parameters and a discussion of contaminated data issue. Also, this article includes inference for two or more populations of the same structure as the randomized response model introduced.
|