Neutrosophic logistic model with applications in fuzzy data modeling

Abstract

The logistic distribution is frequently encountered to model engineering, industrial, healthcare and other wide range of scientific data. This work introduces a flexible neutrosophic logistic distribution (LDN) constructed using the neutrosophic framework. The LDN is considered to be ideal for evaluating and quantifying the uncertainties included in processing data. The suggested distribution offers greater flexibility and superior fit to numerous commonly used metrics for assessing survival, such as the hazard function, reliability function, and survival function. The mode, skewness, kurtosis, hazard function, and moments of the new distribution are established to determine its properties. The theoretical findings are experimentally proven by numerical studies on simulated data. It is observed that the suggested distribution provides a better fit than the conventional model for data involving imprecise, vague, and fuzzy information. The maximum likelihood technique is explored to estimate the parameters and evaluate the performance of the method for finite sample sizes under the neutrosophic context. Finally, a real dataset on childhood mortality rates is considered to demonstrate the implementation methodology of the proposed model.