Application on wide-ranging estimation of population proportion using auxiliary attributes

Many fields require the development of different techniques and approaches to improve the precision and efficiency of population parameters estimation. To reflect the impact of technology, particularly big data analysis, on the total cost of sampling, researchers must revise their cost models. Therefore, there is still an opportunity to discover more efficient estimators. In this paper, we suggest an enhanced class of estimators for estimation of population proportion using auxiliary attributes under simple random sampling. By comparing the proposed estimator with adopted existing estimators, we may determine its bias and MSE up to the first-order approximation. To check the novelty of estimators we utilize some real data sets and a simulation study. Based on the numerical results, it has been shown that the MSE of the suggested estimators has been found minimum as compared to adopted existing estimators. Based on the theoretical and empirical studies, it has been shown that the suggested estimators perform better in terms of efficiency. The suggested class of estimators is establishing to be more effective than the existing estimators, when estimating the population proportion under a given condition.