ANALYSIS OF MULTIFACTOR IMPRECISE DATA USING NEUTROSOPHIC STATISTICS
By
Pranesh Kumar
Department of Mathematics and Statistics, Faculty of Science and Engineering,
University of Northern British Columbia, Prince George, BC V2N4Z9, Canada
Email: pranesh.kumar@unbc.ca
(Received: January 14, 2024; In format: January 17, 2024; Revised: March 27, 2024; Accepted: April 04, 2024)
DOI: https://doi.org/10.58250/jnanabha.2024.54117
Abstract
In multifactor experiments, data collected may correspond to the categorical variables, which place individuals/items into one of several groups (categories). The values of a categorical variable are levels for the categories and distribution of a categorical variable lists the count or percent of individuals/items falling into each category. For example, a two-way table describes two categorical variables by arranging counts according to a row variable and a column variable and each combination of values for two variables is called a cell. However, sometimes a few or every cell counts may be imprecise numbers because of missing or incomplete information on the sample individuals, or investigators negligence, or any other reasons. In such situations, data need to be analyzed using neutrosophic logic and neutrosophic statistics. Generally, the objective of contingency table analysis is to study goodness of model fit for discrete or continuous distributions, testing for homogeneity, and testing for independence. In this paper, we consider neutrosophic analysis of categorical data, which is arranged in contingency tables. We discuss results obtained from the neutrosophic contingency table analysis using data observed in various applications.
2020 Mathematical Sciences Classification: 62H17, 62H20, 62A86
Keywords and Phrases: Categorical data, contingency tables, neutrosophic data, neutrosophic statistics.