الفهرس | Only 14 pages are availabe for public view |
Abstract Ranked set sampling approach is considered a cost-efficient alternative to simple random sampling when observations are costly or time-consuming but the ranking of the observations without actual measurement can be done relatively easily. Many authors suggested different modifications for ranked set sampling to come up with new sampling techniques. Median ranked set sampling, extreme ranked set sampling, neoteric ranked set sampling and partial ranked set sampling are some modifications for ranked set sampling. In this thesis, the estimation of R=P (Y < X) when X and Y are two independent generalized exponential distributions with the same known shape parameter is considered. Maximum likelihood method is proposed to estimate R based on ranked set sampling, median ranked set sampling, extreme ranked set sampling, neoteric ranked set sampling and partial ranked set sampling data. These estimators are compared with known estimators based on simple random sampling, ranked set sampling and neoteric ranked set sampling in terms of their mean square errors and efficiencies. To our knowledge, in the literature, there were no studies that had been performed about stress-strength problem incorporating multicomponent based on neoteric ranked set sampling technique. The research methodology adapted here is to estimate the reliability by using maximum likelihood method of estimation. Based on different types of ranked set sampling, the reliability estimators for strength stress model are obtained when samples drawn from generalized exponential distributions. Numerical study is conducted to compare the efficiencies of reliability estimators based on ranked set sampling, median ranked set sampling, extreme ranked set sampling neoteric ranked set sampling and partial ranked set sampling with respect to reliability estimators based on ranked set sampling and neoteric ranked set sampling procedure. |