Asymptotic derivation of T* statistic
Monitoring the stability of correlation structure becomes an imperative subject in economic development and financial industry. It has been extensively implemented by various researchers to understand the behaviour of a sequence of correlation structures based on independent samples in certain time...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
American Institute of Physics Inc.
2014
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/51959/ http://dx.doi.org/10.1063/1.4903691 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Summary: | Monitoring the stability of correlation structure becomes an imperative subject in economic development and financial industry. It has been extensively implemented by various researchers to understand the behaviour of a sequence of correlation structures based on independent samples in certain time periods. The existing statistical test can only tackle problems involving p<n. However, it is fails to handle p>n due to the inversion of covariance matrix. Therefore, in this paper we introduced T∗ statistics, constructed based on upper-off-diagonal elements to overwhelm that difficulty. The limitation distribution has been investigated to make its application promising. |
|---|