Article Sidebar
Published:
Mar 4, 2025Keywords:
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
(i) AJER is an open-access journal. This means that all content is freely available to all. The author retains the copyrights associated with their work within AJER’s policy framework.
(ii) All articles can be accessed freely without any limitations of use, distribution, and reproduction in any medium so long as they are expressly cited.
(iii) The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, may not mean that these names are not protected by the relevant laws and regulations in their respective countries.
(iv) The publisher believes that all information is true and accurate at the time of going to press. In this regard, the authors, editors, and publishers cannot accept any legal responsibility for any errors, typos or omissions that may be made. There is thus no warranty for the materials contained in the articles.
Main Article Content
A New Bivariate Family of Distributions Based on the Clayton Archimedean Copula and Dagum Distribution
Julius Kwaku Adu-Ntim
Abstract
This study introduces a novel bivariate distribution combining the Clayton Archimedean copula and the Dagum distribution, addressing challenges in modeling complex dependencies, skewness, heavy tails, and multimodal distributions. The proposed NBCDagE distribution leverages the Clayton copula’s ability to capture asymmetric dependencies and the Dagum distribution’s flexibility to model diverse data behaviors, making it suitable for reliability, finance, and survival analysis applications. Key statistical properties of the NBCDagE distribution, including the probability density function (PDF), cumulative distribution function (CDF), product and joint moments, and Shannon entropy, were derived and analyzed. The model demonstrates sensitivity to parameter changes, with higher parameter values leading to sharper PDFs and lighter tails, while lower values result in flatter PDFs and heavier tails. Joint moments and entropy analyses revealed the distribution’s ability to adapt to varying data complexities, showcasing its robustness in capturing dependence structures and marginal characteristics. Visual representations, including contour plots and density curves, illustrate the flexibility of the NBCDagE model in handling a wide range of dependence patterns and data structures. The distribution’s performance was further validated through theoretical derivations and numerical examples, highlighting its adaptability and precision in multivariate data modeling. In conclusion, the NBCDagE distribution provides a robust framework for analyzing bivariate data with intricate dependency structures. Its flexibility and statistical rigor make it a valuable tool for diverse applications, paving the way for future research in higher-dimensional extensions and practical implementations.
