Analysis of Survival Data with Dependent Censoring
Analysis of Survival Data with Dependent Censoring
复制标题
DOI：
10.1007/978-981-10-7164-5
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
T. Emura;Yi-Hau Chen
中科院分区：
文献类型：
--
作者：
T. Emura;Yi-Hau Chen
这本书介绍了copula为基础的统计方法来分析生存数据，涉及相关删失。这本书解释了为什么在医学研究中会出现相关审查的问题，并说明了基于Copula的统计方法如何解决这个问题。这本书介绍了各种基于Copula的方法来处理相关删失，包括Copula图形估计，参数/半参数最大似然估计，单变量选择方法和预测方法。本书还介绍了Copula的基本理论，用于对二元生存数据进行建模。关于生存分析的一般书籍有很多，例如Kalbfleisch和普伦蒂斯（2002）、Lawless（2003）、Klein和Moeschberger（2003）以及Collett（2003，2015）。这些书重点关注在独立审查假设下开发的标准统计方法。尽管如此，所有这些书都提到了在将标准方法应用于真实的数据时仔细检查独立删失假设的重要性。Kalbfleisch和普伦蒂斯（2002）、Lawless（2003）以及Klein和Moeschberger（2003）提供了竞争风险方法来处理相依删失而不使用Copula。Collett（2015）在他最新版本的《医学研究中的生存数据建模》中增加了一个新的章节“相依删失”，介绍了一些处理相依删失的技术。我们的书介绍了各种基于Copula的统计方法，这些方法在上面列出的书中没有讨论。我们的重点是来自医学研究的生存数据。我希望这本书能吸引那些在医疗和制药机构工作的（生物）统计学家。当然，这本书中提出的统计方法可以是v
This book introduces copula-based statistical methods to analyze survival data involving dependent censoring. This book explains why the problem of dependent censoring arises in medical research, and illustrates how copula-based statistical methods remedy the problem. This book introduces a variety of copula-based methods to deal with dependent censoring, including the copula-graphic estimator, parametric/semi-parametric maximum likelihood estimators, univariate selection method, and prediction method. This book also introduces the basic theory of copulas for modeling bivariate survival data. There are many general books on survival analysis such as Kalbfleisch and Prentice (2002), Lawless (2003), Klein and Moeschberger (2003), and Collett (2003, 2015). These books focus on the standard statistical methods that have been developed under the assumption of independent censoring. Nonetheless, all these books mention the importance of scrutinizing the independent censoring assumption when applying the standard methods to real data. Kalbfleisch and Prentice (2002), Lawless (2003), and Klein and Moeschberger (2003) provide competing risks approaches to deal with dependent censoring without using copulas. In his latest edition of “Modelling Survival Data in Medical Research,” Collett (2015) added a new chapter,“Dependent Censoring,” where some techniques of dealing with dependent censoring are introduced. Our book introduces a variety of copula-based statistical methods that are not discussed in the above-listed books. Our emphasis is placed on survival data arising from medical studies. I hope that this book appeals to those working as (bio) statisticians in medical and pharmaceutical institutes. Of course, statistical methods presented in this book can be v