Improved estimation of population parameter in the existence of non-response using auxiliary information

In many domains, including healthcare, economics, and weather forecasting, estimating the finite population mean using non-response is an essential and practically useful task. The mean estimation is heavily used by actuaries and insurance analysts for the purpose of making insightful conclusions. To improve the precision of estimators in survey samples, auxiliary variables play a crucial role. Based on simple random sampling, this study suggests a novel family of estimators that are better designed for determining the population mean using data which include non-response. Efficiency requirements are determined by comparing the mean squared errors of the suggested class of estimators with existing counterparts. The empirical study makes use of both real life data sets and a simulation study. The empirical results show clearly that the proposed estimators are better than the existing estimators. The biases and mean square errors of these estimators, among their other attributes, have been thoroughly examined and explored through numerical and simulation studies. The recommended estimators perform well for the population mean in terms of minimum MSEs and higher percentage relative efficiency.