Testing and Estimation of Econometric Models

计量经济模型的检验和估计

• 批准号: 9410675
• 负责人: Donald Andrews
• 金额: $ 23.16万
• 依托单位: Yale University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1995
• 资助国家: 美国
• 起止时间: 1995-03-15 至 1998-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9410675&HistoricalAwards=false
• 关键词: Testing; Estimation; Econometric; Models

This project consists of five areas of research. The first involves testing hypotheses with a restricted parameter space. This research will focus on the development of new tests that possess optimality properties and on the question of whether the likelihood ratio test is asymptotically admissible. The second area involves testing hypotheses when a nuisance parameter is present only under the alternative hypothesis. This research will also focus on developing new tests that have optimality properties for testing for random parameter variation. The third area involves estimation of the intercept of a semiparametric selection model. The forth area involves the estimation of nonlinear models with time trends. Research in this area will consider asymptotics for nonlinear estimators and models for data that exhibit deterministic and stochastic trends. The final area of research will focus on testing when a nuisance parameter is present only in parts of the null hypothesis.

该项目包括五个研究领域。 第一个涉及用有限的参数空间检验假设。 本研究将重点关注开发具有最优性的新检验，以及似然比检验是否渐近可接受的问题。 第二个领域涉及当干扰参数仅在备择假设下存在时测试假设。 这项研究还将重点开发具有最优特性的新测试，用于测试随机参数变化。 第三个领域涉及半参数选择模型的截距估计。 第四个领域涉及具有时间趋势的非线性模型的估计。 该领域的研究将考虑非线性估计量的渐近以及表现出确定性和随机趋势的数据模型。 最后一个研究领域将集中于测试何时仅在零假设的部分中存在令人讨厌的参数。