Dealing with missingness in uncertain data via neutrosophic exponential imputation: Climate data insights

Anoop Kumar; Vishal Kumar; Vrijesh Tripathi

Authors

Anoop Kumar Department of Statistics, Central University of Haryana, Mahendergarh, Haryana, India, 123031
Vishal Kumar Department of Statistics, Central University of Haryana, Mahendergarh, Haryana, India, 123031.
Vrijesh Tripathi Depatment of Mathematics and Statistics, The University of The West Indies St. Augustine, Trinidad and Tobago.

Keywords:

Neutrosophic sets; Uncertainty; Climate data; Exponential imputation approaches; Missing data

Abstract

Missing data is a common problem across numerous real-world datasets, particularly in domains
such as climate research where data is frequently inadequate because of environmental conditions, defective
sensors or human mistakes. Due to the inherent uncertainty in these datasets, traditional imputation approaches
produce inefficient estimates. Neutrosophy offers a strong framework for managing uncertainty because of its
ability to express truth, falsehood, and indeterminacy concurrently. This work presents some neutrosophic
exponential imputations and the corresponding neutrosophic exponential estimators of the population mean for
handling missing values in uncertain data, with a focus on climate data. The proposed neutrosophic exponential
imputations and the corresponding estimators are exemplified through a comprehensive simulation study and
a real climate dataset. The findings indicate that the proposed neutrosophic exponential imputations and
the corresponding estimators perform better at maintaining data integrity and increasing estimation accuracy
compared to the adapted ones.

DOI 10.5281/zenodo.19701342