Inference in Regression Models with Missing Covariates

缺少协变量的回归模型中的推理

• 批准号: 7651933
• 负责人: JOSEPH G IBRAHIM
• 金额: $ 38.47万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 1997
• 资助国家: 美国
• 起止时间: 1997-09-01 至 2011-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7651933
• 关键词: Acquired Immunodeficiency Syndrome; Address; Cardiovascular Diseases; Chronic Disease; Collaborations; Data; Data Set; Development; Diagnostic; Environmental Health; Grant; Influentials; International Breast Cancer Study Group; Linear Models; Longitudinal Studies; Malignant Neoplasms; Malignant neoplasm of lung; Malignant neoplasm of prostate; Measures; Methodology; Methods; Modeling; Philosophy; Property; Regression Analysis; Residual state; Scheme; Statistical Models; Testing; Veterans; Work; base; cooking; health administration; malignant breast neoplasm; response; statistics; tool

In this proposal, we propose Bayesian and frequentist methodology for local influence diagnostics and develop model assessment tools for complete data settings as well as in the presence of missing covariate and/or response data for a variety of statistical models, including generalized linear models, models for longitudinal data, and survival model. In Specific Aim 1, we develop frequentist local influence measures and goodness of fit statistics based on the general local influence development of Cook (1986), and discuss these measures for i) linear models with missing at random (MAR) and nonignorably missing covariates and ii) generalized linear models with MAR and nonignorably missing covariates. For Specific Aim 2, we develop new classes of Bayesian case influence diagnostics for the complete data setting then generalize these diagnostics to the missing data framework. The proposed methodologies in Aims 1-2 are primarily motivated from several studies in the PI’s collaborative work.

在这项提案中，我们提出了贝叶斯和频率论方法的局部影响诊断和开发完整的数据设置，以及在存在缺失的协变量和/或响应数据的各种统计模型，包括广义线性模型，纵向数据模型和生存模型的模型评估工具。在具体目标1中，我们在Cook（1986）的一般局部影响发展的基础上发展了频率局部影响测度和拟合优度统计量，并讨论了i）具有随机缺失（MAR）和不可重复缺失协变量的线性模型和ii）具有MAR和不可重复缺失协变量的广义线性模型的这些测度。对于特定目标2，我们开发了新的贝叶斯案例影响诊断类的完整的数据设置，然后将这些诊断推广到缺失的数据框架。目标1-2中提出的方法主要来自PI合作工作中的几项研究。