Simulation based evaluation of neutrosophic exponential imputations of population mean using neutrosophic ranked set sampling

The prevalence of missing values and uncertainty in real-world dataset often hinders accurate analysis and reliable conclusions. Existing approaches often struggle to effectively address both aspects simultaneously. To handle both these aspects simultaneously, this paper proposes an approach that combines neutrosophic theory with exponential imputation and provides neutrosophic exponential imputations for estimating population mean using neutrosophic ranked set sampling (NRSS) framework. Neutrosophic imputation structures utilize the strengths of neutrosophic logic to manage uncertainty inherent in the data and incorporates NRSS to improve the efficiency of the imputation process. The mathematical properties such as bias and mean square error (MSE) of the proposed neutrosophic exponential estimators are obtained. The proposed neutrosophic exponential imputations are compared with some adapted prominent neutrosophic imputations. A thorough simulation study demonstrates that neutrosophic exponential imputations outperform the adapted prominent imputation structures in terms of both accuracy and robustness in handling datasets characterized by both missingness and uncertainty. A real data application of the proposed imputation structures is also presented in support of the mathematical results as well as simulation findings.