Rank set sampling in improving the estimates of simple regression model

Abstract

In this paper Rank set sampling (RSS) is introduced with a view of increasing the efficiency of estimates of Simple regression model. Regression model is considered with respect to samples taken from sampling techniques like Simple random sampling (SRS), Systematic sampling (SYS) and Rank set sampling (RSS). It is found that R2 and Adj R2 obtained from regression model based on Rank set sample is higher than rest of two sampling schemes. Similarly Root mean square error, p-values, coefficient of variation are much lower in Rank set based regression model, also under validation technique (Jackknifing) there is consistency in the measure of R2, Adj R2 and RMSE in case of RSS as compared to SRS and SYS. Results are supported with an empirical study involving a real data set generated of Pinus Wallichiana taken from block Langate of district Kupwara.