Reduced-rank estimation of the difference between two covariance matrices

作者：Schott James R^*

来源：Journal of Statistical Planning and Inference, 2010, 140(4): 1038-1043.

DOI：10.1016/j.jspi.2009.10.005

• Comparison of covariance matrices
• Likelihood ratio test
• Maximum likelihood estimators

We consider in m x m covariance matrices, Sigma(1) and Sigma(2), which satisfy Sigma(2) - Sigma(1) = Delta, where Delta has a specified rank. Maximum likelihood estimators of Sigma(1), and Sigma(2) are obtained when sample covariance matrices having Wishart distributions are available and rank(Delta) is known. The likelihood ratio statistic for a test about the value of rank(Delta) is also given and some properties of its null distribution are obtained. The methods developed in this paper are illustrated through an example.

• 出版日期2010-4