On estimating the odds using Moving Extreme Ranked Set Sampling

In this paper, the estimation of the odds F/(1−F)F/(1−F) is considered based on Moving Extreme Ranked Set Sampling (MERSS), a variation of Ranked Set Sampling. The suggested estimator based on MERSS is motivated by some of the theoretical properties of the sum of geometric series. The new estimator and the naive estimator based on simple random sample (SRS) are compared via their mean squared errors. It turned out that the estimator based on MERSS is always valid and can have some advantages over that based on SRS. Data from a level I Trauma center are used to illustrate the procedures developed in this paper.