Dani Andrea Tri Rian, Oktavia Nurul Tri
Statistics Study Program, Department of Mathematics, Faculty of Mathematics and Natural Sciences, Mulawarman University, Indonesia.
MethodsX. 2024 Dec 12;14:103082. doi: 10.1016/j.mex.2024.103082. eCollection 2025 Jun.
The Weibull regression model is a regression model derived from the Weibull distribution, where the Weibull distribution is influenced by covariates. In this study, parameter estimation for the Weibull regression model was conducted using the Maximum Likelihood (ML) estimation. The aim of the study is to develop a Weibull regression model based on the hospitalization time of stroke patients at Abdul Wahab Sjahranie Hospital, Samarinda, during the period of 2021-2022, and to identify the factors affecting it. The event of interest in this study is patient recovery. The results indicate that the ML estimator of the Weibull regression model was obtained numerically using the Newton-Raphson iterative. The factors influencing the Weibull regression model include age, body mass index (BMI), and a history of diabetes mellitus. An increase in patient age and a history of diabetes mellitus are associated with an increase in the probability of the patient not recovering, a decrease in the likelihood of recovery, a lower recovery rate, and a longer recovery time. In contrast, an increase in BMI is associated with a decrease in the probability of the patient not recovering, an increase in the likelihood of recovery, a higher recovery rate, and a shorter recovery time. Some highlights in this article, the proposed method are:•We present The Weibull distribution influenced by covariates is called the Weibull regression model•The potential recovery of stroke disease and the factors that influence it can be analyzed through Weibull regression modeling.•The chance of a patient not recovering is modeled through a Weibull survival regression model, the chance of a patient recovering is modeled through a Weibull cumulative distribution regression model, the patient's recovery rate is modeled through a Weibull hazard regression model, and the average patient hospitalization time is modeled through a Weibull mean regression model.
威布尔回归模型是一种源自威布尔分布的回归模型,其中威布尔分布受协变量影响。在本研究中,使用最大似然(ML)估计对威布尔回归模型进行参数估计。本研究的目的是基于2021年至2022年期间 Samarinda 的 Abdul Wahab Sjahranie 医院中风患者的住院时间建立威布尔回归模型,并确定影响该模型的因素。本研究关注的事件是患者康复。结果表明,威布尔回归模型的ML估计量是通过牛顿-拉夫逊迭代法数值获得的。影响威布尔回归模型的因素包括年龄、体重指数(BMI)和糖尿病史。患者年龄的增加和糖尿病史与患者未康复的概率增加、康复可能性降低、康复率降低以及康复时间延长相关。相比之下,BMI的增加与患者未康复的概率降低、康复可能性增加、康复率提高以及康复时间缩短相关。本文的一些亮点,即所提出的方法有:•我们提出受协变量影响的威布尔分布称为威布尔回归模型•中风疾病的潜在康复情况及其影响因素可通过威布尔回归建模进行分析。•通过威布尔生存回归模型对患者未康复的概率进行建模,通过威布尔累积分布回归模型对患者康复的概率进行建模,通过威布尔风险回归模型对患者的康复率进行建模,通过威布尔均值回归模型对患者的平均住院时间进行建模。