Predictive estimation approach using difference and ratio type estimators in ranked set sampling.

In this article, we introduce the predictive estimation approach for estimating the population mean using modified difference and ratio type predictive estimators in ranked set sampling. The expressions of bias and mean square error of the proffered predictive estimators are reported to the first order of approximation. A comparative study of the proffered predictive estimators with the conventional predictive estimators under simple random sampling and ranked set sampling is considered. The theoretical findings have been supported by a broad spectrum computational study carried out using various real and simulated data sets. Further, the appropriate suggestions are forwarded to the survey professionals. [ABSTRACT FROM AUTHOR]