欠測値データを含む平均ベクトルに関する多重比較法を非正規性による影響

非正态性对包含缺失值数据的均值向量的多重比较方法的影响

• 批准号: 11780175
• 负责人: 瀬尾 隆
• 金额: $ 0.7万
• 依托单位: Tokyo University of Science
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Encouragement of Young Scientists (A)
• 财政年份: 1999
• 资助国家: 日本
• 起止时间: 1999 至 2000
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-11780175/
• 关键词: 多重比較; 同時信頼区間; 楕円分布; 非正規性; ロバストネス; 平均ベクトル; 漸近展開

複数個の多変量母集団またはグループの平均ベクトルの同等性検定に関する多重比較法および同時信頼領域の構成について,昨年度から議論してきた完全データかつ多変量正規母集団の拡張である楕円母集団下での同時信頼領域の構成の核となる相関をもつホテリングの最大値統計量分布の修正2次近似法による漸近展開式をまとめ,大規模なモンテカルロシミュレーションを行って,非正規性による影響について調べた.成果は論文としてまとめ,学術雑誌に投稿中である.さらに,欠測値データある場合の平均の同等性検定およびある種の同時信頼区間の構成について,国内大学の専門的知識をもつ研究者と情報交換,討論を行い,また,この分野の研究の第一人者であるカナダのトロント大学のSrivastava教授との討論およびレビューを受け,学術論文としてまとめた.その成果は,Biometrical Journal vol.42に"Testing Equality of Means and Simultaneous Confidence Intervals in Repeated Measures with Missing Data"というタイトルで掲載された.また,2000年12月19日から1999年12月21日においてインドのムンバイにあるIndian Institute of Technology-Bombayで行われた国際会議「International Conference on Statistics,Combinatorics and Related Areas and the Seventh International Conference of the Forum for Interdisciplinary Mathematics」にて,掲載された上記論文と同じ題目で口頭発表し,研究成果を知ってもらうと同時にさらなる知識を深めた.

Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Variable Regular Parent Groups for Determining the Equivalence of Multiple Variable Parent Groups and Simultaneous Information Domain Composition; Multiple Comparison Method for Determining the Maximum Value Statistics Distribution; and Modified Second Approximation Method for Estimating the Asymptotic Expansion Large-scale, irregular, and irregular influences on the behavior of the population. The results of the paper are published in the journal. In addition, the average equivalence of unmeasured values in different situations is determined by the composition of simultaneous information intervals, and the knowledge of domestic universities is exchanged between researchers and information exchanges, discussions are conducted, discussions are conducted, and the first person in the field of research is accepted by Professor Srivastava of the University, academic papers are discussed. "Testing Equality of Means and Simultaneous Confidence Intervals in Repeated Measures with Missing Data," Biometric Journal vol. 42. December 19, 2000-December 21, 1999 Indian Institute of Technology-Bombay International Conference on Statistics,Combinatorics and Related Areas and the Seventh International Conference of the Forum for Interdisciplinary Mathematics The results of the research are as follows:

项目成果

Takashi Seo: "Testing Equality of Means and Simultaneous Confidence Intervals in Repeated Measures with Missing Data"Biometrical Journal. 42・8. 981-993 (2000)

Takashi Seo：“用缺失数据测试重复测量中的均值和同时置信区间”生物统计杂志 42・8 (2000)。