Optimal Neutrosophic Difference to Log-Type Estimator for Population Mean: Some Numerical and Simulation Studies

Indeterminacy in the data are commonly observed in various fields like biomedicine, finance, marketing and other sphere of sciences, where classical statistical methods is a challenging task to deal such type of data. This situation may be effecitively handled under neutrosophic framework. In this paper, we proposed a novel optimal neutrosophic difference to log-type estimator for estimation of population mean, utilizing the dual of an auxiliary variable. We derived the expression for bias and mean squared error (MSE) of the proposed estimator up to the first-order of approximation and determined optimal situation for real constants based on minimum MSE values. We conducted a numerical study using two real-life datasets related to temperature and atmospheric conditions and the results are validated through a simulation study consisting two artificially generated datasets. The findings indicates that the proposed neutrosophic estimator exhibited greater efficiency compared to existing estimators when dealing with uncertain, indeterminate, interval and neutrosophic data. These results highlights its potential applicability in analyzing uncertain or interval-valued data across various scientific domains, including environmental monitoring, social sciences and atmospheric sciences.