Asymptotic properties of a correlation matrix under a two-step monotone incomplete sample

详细信息    查看全文

• 作者：Shin-ichi Tsukada ^{tsukada@ed.meisei-u.ac.jp" class="auth_mail" title="E-mail the corresponding author}
• 关键词：62H10 ; 62E20
• 刊名：Linear Algebra and its Applications
• 出版年：2016
• 出版时间：1 January 2016
• 年：2016
• 卷：488
• 期：Complete
• 页码：86-101
• 全文大小：307 K

文摘

This paper derives an asymptotic distribution for a correlation matrix in the context of a two-step monotone incomplete sample drawn from 47a19e23676f2a168e64d2" title="Click to view the MathML source">N_p+q(μ,Σ)$N_{p+q}(\mathit{\mu },\mathbf{\Sigma })$, a multivariate normal population with mean μ and covariance matrix Σ. Based on the result, we perform hypothesis testing for the correlation matrix and investigate its accuracy using numerical simulations.