Lifetime data analysis is at the forefront of applied science, affecting diverse fields such as engineering, medicine and finance. Traditional models such as exponential and Lindley distribution have their advantages, but are often lacking in capturing the complexity of real-life phenomena. Enter the Suja distribution, a new model that is expected to adopt a more suitable method for analyzing lifelong data. Its introduction marks a more accurate understanding of the dynamics of failure and survival, providing enhanced flexibility and reliability for analyzing such critical data.
In a landmark study published in the Alexander Journal of Engineering, Professor Hanaa Abu-Zinadah and Tamadur Alsumairi of the University of Jeddah introduced a groundbreaking statistical model called the Suja Distribution. This innovative single-parameter distribution provides a novel approach to modeling lifetime data, which is critical for a wide range of applications from engineering to financing. Their exploration of various estimation methods goes beyond traditional maximum likelihood estimation, thereby significantly improving the accuracy and reliability of statistical inference.
The initiative led by Professors Abu Zinada and Professor Alsumali aims to develop a more adaptive approach to modeling life data, which marks a critical moment in the study of life distribution. “In addition, a new one-parameter distribution, called the “Suja distribution”, was suggested and studied, for modeling lifetime data. The estimated values of its parameters have been explored using methods of maximum likelihood estimation and moment. Explore here In contrast to these lifetime distributions called SUJA distributions (SDs), we employ a flexible single-parameter distribution to model lifetime data and reliability,” Alsumairi explains.
Suja’s adaptability distributed in accurately modeling the failure time of a product (critical to assess product quality and reliability) is at the heart of its exploration. By conducting a comprehensive Monte Carlo simulation study, Professors Abu Zinada and Professor Alsumali were able to evaluate and compare the performance of different estimators of Suja parameters, demonstrating their excellent adaptability and reliability in various real datasets .
“We aim to develop SD estimation through different classical methods. In addition, we performed well on three real fit tests.
Exploring methodologies including least squares, weighted least squares and estimators based on percentiles, which demonstrates the flexibility of Suja distribution in different situations. “When data are derived by fitting a straight line to a theoretical point obtained from the distribution function and the sample percentage point, the estimated data is relatively normal for unknown parameters derived from the distribution function with closed form. This method has been used for estimation Many parameters of distributions.” Alsumairi explained, explaining the practicality of their approach.
This comprehensive exploration opens new avenues for statistical modeling and promises to make significant progress in reliability analysis and other areas. The robust and adaptable Suja distribution is a groundbreaking innovation that guides Professors Abu-Zinadah and Professor Alsumairi’s more precise and meaningful analysis of lifelong data. The maximum likelihood estimation (MLE) of the SUJA distribution, as well as the probability density function (PDF) and hazard failure rate (HFRS), are detailed, and their work is also supplemented. This is elucidated by a Monte Carlo simulation study that evaluates the performance of various estimators, demonstrating the reliability and adaptability of distributions without delving into over-technical terms.
Journal Reference
Hanaa Abu-Zinadah, Tamadur Alsumairi, “Estimation of Suja Distribution Parameters Using Applications”, Alexandria Engineering Journal, 2024. DOI: https://doi.org/10.1016/j.aej.aej.2023.11.069.
About the author
Hanaa Abu-Zinadah He is a professor of mathematics statistics at the School of Science, Jeddah University, Jeddah, Kingdom of Saudi Arabia. She was born in Jeddah, the Kingdom of Saudi Arabia in April 1976.
She received a bachelor’s degree in mathematics (1996), a master’s degree (2001) and a doctorate degree. Degree in Mathematics Statistics Department (2006), Department of Science, College of Women’s Education in Jeddah, Kingdom of Saudi Arabia.
From 2010 to 2019, she became the head of the Department of Statistics in the College of Sciences – Jeddah, Jeddah, Jeddah.
Her research spans statistics, including distribution theory, statistical inference, sequential statistics and simulation studies. Her expertise extends to a wide range of programming languages and statistical tools, allowing her to delve into complex analytical and statistical quality controls.
Her work significantly affects the fields of statistical science and interdisciplinary research. Her research output, including papers on various mathematical models and their actual meanings, demonstrates the fusion of the rigorous correlation of theory with the real world.
She continues to work to mentor graduate students’ statistical research and mentoring, which reflects the commitment to shaping the future of statistical science. Her contribution will undoubtedly inspire further advancement and innovation in statistical methods and their applications.
Email: [email protected]
Tamadur Alsumairi is a statistical researcher and data analyst with a master’s degree in statistics (2024), from the Faculty of Science, Department of Mathematics and Statistics, University of Jeddah, Saudi Arabia. She also holds a bachelor’s degree in science system project from the Department of Statistics, King Abdulaziz University, Jeddah, Saudi Arabia (2016).
She is passionate about digital and data analytics and devotes her academic and career to the field of statistics. Her educational background gives her an in-depth understanding of statistical methods, mathematical modeling and data interpretation.
In her research, she gained practical experience in various statistical techniques such as hypothesis testing, regression analysis, time series analysis, and multivariate analysis. She also gained proficiency in programming languages commonly used in statistical analysis, such as R and data analysis using Excel and SPSS. In addition, she used the Mathematica program to estimate parameters, perform numerical simulations, and apply actual data in scientific research.
Her academic journey provides her a solid foundation for statistical research and analysis, enabling her to efficiently collect, organize and analyze complex data sets. She is good at data visualization and can effectively convey statistical findings and insights. She is detailed, analytical, and has strong problem-solving skills.
She is excited about the opportunity to apply her statistical knowledge and analytical abilities to contribute to organizations that need data-driven insights. She has been seeking to expand her knowledge and learn about the latest advances in statistical methods and data analysis techniques. Email: [email protected].
