Comprehensive Class Of Estimators For Estimation Of Population Mean Under Stratified Sampling: Application With Real Data Sets And Simulation Analysis

Abstract

Survey sampling focuses significantly on auxiliary information to provide precise parameter estimates (mean, variance, distribution function, etc.) in order ensure the best possible result. To find the mean value of an investigated variable in the population, this study makes use of additional information. The primary objective of this research is to create an improved estimator of a finite population's mean by using information from an auxiliary variable in stratified random sampling. Up to the first order of approximation, the bias and mean square error (MSE) expressions of the suggested estimator are inferred. We show that these proposed estimators perform well during the estimation process by doing a thorough analysis utilizing criteria like percentage relative efficiency and mean square error. In addition, we conduct a thorough simulation study to demonstrate that our suggested estimate exceeds other estimators that have been addressed in the literature, including conventional unbiased estimators and traditional regression estimators. Our proposed estimator appears to be the best option when compared to numerous other methods. In addition to making significant advancements in the area of survey sampling methods, the study findings give crucial information for predictive modeling on real data sets.