الفهرس | Only 14 pages are availabe for public view |
Abstract The Non-Randomized Response (NRR) technique is a procedure that can be used in surveys with sensitive questions. In this thesis, some of the existing NRR models are extended to stratified random sampling. Efficiency comparisons between the extended models are then carried out. Moreover, three new improved non-randomized response models are proposed. The first proposed model is the alternating parallel model which is built on relaxing one of the assumptions of the parallel model. The second model is the non-randomized version of Sayed and Mazloum (2020) model, and the third proposed model is the parallel model under non-compliance. Finally, the efficiency of the proposed models is discussed |