Asymptotic expansion of the null distribution of the modified normal likelihoodratio criterion for testing $\Sigma=\Sigma_0$ under nonnormality

スポンサーリンク

概要

• 論文の詳細を見る

• This paper is concerned with the null distribution of themodified normal likelihood ratio criterionfor testing the null hypothesisthat a covariance matrix is a given one, i.e.,$\Sigma=\Sigma_0$, under nonnormality.We obtain an asymptotic expansion of the null distributionof the test statistic up to the order $n^{-1}$,where $n$ is the sample size, under nonnormalityby using an Edgeworth expansion of the density function of a samplecovariance matrix.

• 広島大学の論文

著者

• Tonda Tetsuji

  Department Of Environmetrics And Biometrics Research Institute For S Adiation Biology And Medicine H

• Tonda Tetsuji

  Department Of Environmentrics And Biometrics Research Institute For Radiation Biology And Medicine H

• Yanagihara Hirokazu

  Institute of Policy and Planning Sciencs, University of Tsukuba

• Matsumoto Chieko

  Department ofMathematics, GraduateSchool of Science, Hiroshima University

• Yanagihara Hirokazu

  Institute Of Policy And Planning Sciencs University Of Tsukuba

• Matsumoto Chieko

  Department Of Mathematics Graduate School Of Science Hiroshima University

• Matsumoto Chieko

  Department Ofmathematics Graduateschool Of Science Hiroshima University

関連論文

• Asymptotic expansion of the null distribution of the likelihood ratio statistic for testing the equality of variances in a nonnormal one-way ANOVA model
• Asymptotic expansion of the null distribution of the modified normal likelihoodratio criterion for testing $\Sigma=\Sigma_0$ under nonnormality
• A class of multivariate discrete distributions based on an approximate density in GLMM
• Adjustment on an asymptotic expansion of the distribution function with $χ^2$-approximation
• An optimal discriminant rule in the class of linear and quadratic discriminant functions for large dimension and samples

スポンサーリンク