参数竞争风险分位数模型  

Parametric competing risks quantile model

作　　者：胡军浩[1] 黄荧 杨青 HU Junhao;HUANG Ying;YANG Qing(College of Mathematics and Statistics,South-Central Minzu University,Wuhan 430074,China)

机构地区：[1]中南民族大学数学与统计学学院,武汉430074

出　　处：《中南民族大学学报（自然科学版）》2022年第6期749-755,共7页Journal of South-Central University for Nationalities：Natural Science Edition

基　　金：国家自然科学基金资助项目(61876192);中南民族大学研究生学术创新基金资助项目(3212022sycxjj003)。

摘　　要：竞争风险分位数回归模型通过最小化不连续的L1型凸函数来进行系数推断,其可能会导致多根问题,且结果难以解释.引入线性规格的参数函数,构建了一个新的参数竞争风险分位数模型.利用积分损失最小化方法进行参数估计,解决了解不唯一性问题,极大地提高了估计效率,获得了分位数与估计系数之间的更多信息.对估计量的一致性和渐近正态性进行了分析,给出了模型选择与模型评估过程.通过数值模拟说明了在标准误的意义下,参数结构下的竞争风险分位数模型更有效.最后将模型应用到滤泡细胞淋巴瘤的临床研究中.The competing risks quantile regression model performs coefficient inference by minimizing discontinuous L1-type convex functions,which may lead to multiple roots and the results are difficult to interpret.In this paper,a parametric function of the linear specification is introduced to construct a new parametric competing risks quantile model.Using the integrated loss minimization method for parameter estimation,the problem of non-unique results is solved,the estimation efficiency is greatly improved,and more information between quantiles and estimated coefficients is obtained.The consistency and asymptotic normality of the estimators are analyzed.The process of model selection and model evaluation is given.Numerical simulation shows that under the standard error,the competing risks quantile model under the parameter structure is more effective.Finally,the model is applied to the clinical research of follicular cell lymphoma.

关 键 词：参数化 分位数回归 竞争风险 积分损失最小化 

分 类 号：O212.8[理学—概率论与数理统计] R195.1[理学—数学]