Open Access

Structure identification for a linearly structured covariance matrix: part II

   | Dec 29, 2023

Cite

Covariance matrices with a linear structure are widely used in multivariate analysis. The choice of covariance structure can be made from a set of possible linear structures. As a result, the most appropriate structure is determined by minimizing the discrepancy function. This paper is a continuation of previous work on identifying linear structures with an entropy loss function as a discrepancy function. We present extensive simulation studies on the correctness of identification with the assumed pentagonal banded Toeplitz structure.

eISSN:
2199-577X
Language:
English
Publication timeframe:
2 times per year
Journal Subjects:
Life Sciences, Bioinformatics, other, Mathematics, Probability and Statistics, Applied Mathematics