Gemeay Ahmed M, Sapkota Laxmi Prasad, Tashkandy Yusra A, Bakr M E, Balogun Oluwafemi Samson, Hussam Eslam
Department of Mathematics, Faculty of Science, Tanta University, Tanta 31527, Egypt.
Department of Statistics, Tribhuvan University, Tribhuvan Multiple Campus, Palpa, Nepal.
Heliyon. 2024 Oct 9;10(23):e38965. doi: 10.1016/j.heliyon.2024.e38965. eCollection 2024 Dec 15.
The article introduces a new unit distribution, an extension of Tiessier distribution, characterized by a versatile hazard function capable of adopting diverse shapes such as bathtub or N-shaped curves. An exploration of the fundamental properties of this distribution is undertaken, accompanied by the implementation of the maximum likelihood estimation technique and eleven alternative methods to approximate its parameters effectively. Through a simulation study, the article effectively demonstrates the precision of these parameter estimation methods, even when dealing with small sample sizes. Two datasets are employed to apply the novel distribution, subjecting it to a comprehensive evaluation against established models utilizing a range of model selection criteria and goodness of fit tests. Notably, the article illustrates that the performance of the new distribution surpasses that of existing models in effectively capturing data patterns. Beyond its empirical contributions, the article highlights the potential cross-disciplinary applications of the new distribution in many fields while concurrently advancing the realms of probability theory and statistical inferences.
本文介绍了一种新的单位分布,它是蒂塞尔分布的扩展,其特征在于具有通用的风险函数,能够呈现多种形状,如浴缸形或N形曲线。对该分布的基本性质进行了探索,并实施了最大似然估计技术以及十一种替代方法来有效近似其参数。通过模拟研究,本文有效地证明了这些参数估计方法的精度,即使在处理小样本量时也是如此。使用两个数据集来应用这种新分布,并利用一系列模型选择标准和拟合优度检验,将其与已建立的模型进行全面评估。值得注意的是,本文表明新分布在有效捕捉数据模式方面的性能优于现有模型。除了其实证贡献外,本文还强调了新分布在许多领域的潜在跨学科应用,同时推进了概率论和统计推断领域的发展。