Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1154716 | Statistics & Probability Letters | 2014 | 6 Pages |
Abstract
This paper studies the asymptotic power of the likelihood ratio test (LRT) for the identity test when the dimension pp is large compared to the sample size nn. The asymptotic distribution under local alternatives is derived and a simulation study is carried out to compare LRT with other tests. All these studies show that LRT is a powerful test to detect small eigenvalues.
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
Cheng Wang,