Statistical Methods And Applications For Laboratory Animal Studies

实验动物研究的统计方法和应用

基本信息

批准号：
8553702
负责人：
Gregg Dinse
金额：
$ 0.65万
依托单位：
NATIONAL INSTITUTE OF ENVIRONMENTAL HEALTH SCIENCES
依托单位国家：
美国
项目类别：
财政年份：
资助国家：
美国
起止时间：
至
项目状态：
未结题

项目摘要

The majority of my research on this project was performed in two areas: (1) censored failure-time analysis when some censoring indicators are missing and (2) general analysis of animal carcinogenicity studies. These two areas of research are described in more detail below. Area 1: Failure-time data are typically subject to censoring, such as when a study ends before all participants fail. Additionally, when multiple causes of failure are operating, the time to failure from one cause can be censored by a failure from another cause. In some situations, the censoring indicator is missing for a subset of individuals, such as in a cancer bioassay when the pathologist is not able to determine the role of a tumor in causing death or when some records are incomplete. The analysis of failure-time data typically focuses on hazard functions. Under an accelerated failure-time model, we derived three nonparametric hazard estimators that are appropriate when some failure times are right censored and some censoring indicators are missing. Specifically, we developed a regression surrogate estimator, an imputation estimator, and an inverse probability weighted estimator. All three estimators use kernel smoothing techniques and enjoy certain large-sample properties such as uniform strong consistency and asymptotic normality. A simulation study showed that the proposed hazard estimators also performed well in small samples. We published an article describing this work (see reference 2). Area 2: A three-state stochastic model is often used to analyze carcinogenicity data from long-term rodent bioassays, such as the 2-year studies conducted by the NTP. The most appropriate analysis depends on many factors, such as whether: tumors are observable before death, tumors affect mortality, cause-of-death information is collected, random sacrifices are performed, parametric models are justified, functional constraints are reasonable, or supplemental information (e.g., historical data, additional covariates, expert opinions) is available. An article describing this work is scheduled to appear in December (see reference 1).

我对该项目的大部分研究是在两个领域进行的：（1）当缺少某些审查指标时，审查失败时间分析以及（2）对动物致癌性研究的一般分析。这两个研究领域在下面更详细地描述。区域1：失败时间数据通常受到审查的约束，例如研究在所有参与者失败之前结束时。此外，当失败的多个原因运行时，可能会因另一个原因的失败而审查失败的时间。在某些情况下，一部分个体缺少检查指标，例如在癌症生物测定中，病理学家无法确定肿瘤在造成死亡或某些记录不完整时的作用。故障时间数据的分析通常集中在危险功能上。在加速故障时间模型下，我们得出了三个非参数危害估计器，这些估计值适用于某些故障时间是正确的审查，并且缺少某些审查指标。具体而言，我们开发了回归替代估计量，插补估计器和一个反概率加权估计器。所有三个估计器都使用内核平滑技术，并享受某些大样本特性，例如均匀的强一致性和渐近正态性。一项模拟研究表明，提出的危险估计器在小样品中也表现良好。我们发表了一篇描述这项工作的文章（请参阅参考文献2）。区域2：三态随机模型通常用于分析长期啮齿动物生物测定的致癌性数据，例如NTP进行的两年研究。最合适的分析取决于许多因素，例如：肿瘤在死亡前可观察到，肿瘤会影响死亡率，收集死亡原因，进行随机牺牲，参数模型是合理的，功能性约束是合理的或补充信息（例如，历史数据，其他协会，专家意见，其他协调数据）。一篇描述这项工作的文章计划于12月出现（请参阅参考文献1）。