Factor analysis is a multivariate statistical technique used to explore the relationships among a large number of variables associated with a particular phenomenon, with the goal of reducing the number of variables and creating new, unrelated variables. In our thesis, a novel approach using unified entropy was employed for factor extraction. Similarities and differences between the results obtained from "Factorization" using this unified entropy approach and those from "Exploratory Factor Analysis" were discussed.

A model combining statistics and entropy was utilized, where initially, results from conventional factor analysis commonly used in statistics were obtained. Subsequently, a comparison was made with results derived from an entropy-based approach using a unified entropy matrix instead of the covariance matrix. In this context, the results obtained with the unified entropy matrix were juxtaposed against those obtained through traditional factor analysis. Ultimately, the findings obtained with the unified entropy matrix were presented. Additionally, this study aimed to provide theoretical support for entropy and demonstrate its potential applicability and support in domains traditionally reliant on variance-covariance measures. Despite certain challenges that need to be addressed, this approach is proposed as an alternative to conventional methods.