Mathematical Sciences: Statistical Models and Methods for Incomplete and Biased Data

数学科学：不完整和有偏差数据的统计模型和方法

• 批准号: 8802893
• 负责人: Yehuda Vardi
• 金额: $ 13.05万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1988
• 资助国家: 美国
• 起止时间: 1988-07-01 至 1991-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=8802893&HistoricalAwards=false
• 关键词: Mathematical; Sciences; Statistical; Models; Methods

This research focuses on the development of models and methods for statistical analysis of biased, or incomplete, data. Problems will be tackled in three different general research areas: (1) Estimation in Renewal Processes, (2) Semiparametric Models in Selection Bias, and (3) Statistical Models for Cross Sectional Sampling. This work in statistics aims at improving the tools available for handling sampling bias and incompleteness in data acquisition. The recent spread of the AIDS epidemic, and the behavioral issues involved in sampling, diagnosing, and identifying patients present a pressing need for the development of such methods for a variety of complicated biased-sampling schemes. In developing the statistical models and methods, these issues will be addressed.

本研究的重点是模型的开发， 对有偏差或不完整的数据进行统计分析的方法。 问题将在三个不同的一般性研究中解决 领域：（1）更新过程中的估计，（2）半参数 选择偏倚模型和（3）交叉统计模型 分段取样。 这项统计工作旨在改进统计工具， 可用于处理数据中的抽样偏差和不完整性 采集 最近艾滋病的蔓延， 行为问题涉及采样，诊断， 识别患者是发展的迫切需要， 这种方法的各种复杂的偏置抽样 阴谋 在开发统计模型和方法时， 问题将得到解决。