Inferences on Multivariate Measures of Interclass and Intraclass Correlations in Familial Data
本文提出了多元类间和类内相关性的统一估计量，基于加权平方和乘积矩阵的特征值，并在多元正态假设下推导了渐近分布，从而得到简单的置信区间和检验方法。
SUMMARY Multivariate measures of interclass and intraclass correlations are introduced to assess the degree of resemblance between family members with respect to more than one characteristic. Unified estimators for the multivariate measures are proposed as the eigenvalues of certain random matrices constructed by the matrices of the weighted sums of squares and products of observations. Asymptotic distributions of the proposed estimators are derived under the assumption of multivariate normality. The asymptotic results produce approximate confidence intervals and test procedures in a simple way.