Multivariate Behrens-Fisher problem with missing data

JOURNAL OF MULTIVARIATE ANALYSIS

卷:105

Article

Krishnamoorthy, K.²  Yu, Jianqi¹ 

[1] Shanghai Jiao Tong Univ, Dept Math, Shanghai 200240, Shanghai, Peoples R China

[2] Univ Louisiana Lafayette, Dept Math, Lafayette, LA 70504 USA

关键词: Approximate degrees of freedom solution;    Coverage probability;    Incomplete data;    Maximum likelihood estimators;    Moment approximation;    Sizes;   

DOI  :  10.1016/j.jmva.2011.08.019

来源: Elsevier

【 摘 要 】

Inference about the difference between two normal mean vectors when the covariance matrices are unknown and arbitrary is considered. Assuming that the incomplete data are of monotone pattern, a pivotal quantity, similar to the Hotelling T-2 statistic, is proposed. A satisfactory moment approximation to the distribution of the pivotal quantity is derived. Hypothesis testing and confidence estimation based on the approximate distribution are outlined. The accuracy of the approximation is investigated using Monte Carlo simulation. Monte Carlo studies indicate that the approximate method is very satisfactory even for moderately small samples. The proposed methods are illustrated using an example. (C) 2011 Elsevier Inc. All rights reserved.

【 授权许可】

Free