Survey sampling continues to play a pivotal role in modern statistical research, offering a efficient means of estimating population parameters without requiring a complete enumeration. However, practical data collection frequently involves extreme or atypical observations that, if overlooked, can distort estimation accuracy and lead to biased conclusions. The former research primarily focuses on use of auxiliary information to estimate the population parameters of main variable. The class of estimators suggested in this category one ratio type estimators, product type estimators and regression type estimators. Later, Bahl and Tuteja (1991) suggested a new class of exponential and product estimators. Recent advancements have introduced logarithmic-type estimators, but their statistical properties remain only partially explored. Recognizing this challenge, the present study proposes a refined logarithmic-type estimator for finite population variance within the framework of simple random sampling without replacement (SRSWOR). The estimator incorporates auxiliary information to improve the precision and stability of variance estimation. Theoretical properties, including bias and mean squared error (MSE), are derived up to the first order of approximation, ensuring a rigorous analytical foundation. To assess its performance, comparative and simulation-based analyses are carried out against several existing estimators. The findings reveal that the proposed estimator consistently produces lower MSE values and exhibits greater robustness. These results confirm both the theoretical and empirical superiority of the proposed approach. Overall, the study contributes to the growing body of literature on efficient estimation techniques by presenting a more accurate and reliable alternative for population variance estimation in survey sampling and their applications.
Yadav et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: