Large dimensional empirical likelihood
The empirical likelihood is a versatile nonparametric approach to testing hypotheses and constructing confidence regions. However it is not clear if Wilks’ Theorem still works in high dimensions. In this paper, by adding two pseudo-observations to the original data set, we prove the asymptotic norma...
Saved in:
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/88029 http://hdl.handle.net/10220/46882 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| id |
sg-ntu-dr.10356-88029 |
|---|---|
| record_format |
dspace |
| spelling |
sg-ntu-dr.10356-880292020-03-07T12:31:27Z Large dimensional empirical likelihood Chen, Binbin Pan, Guangming Yang, Qing Zhou, Wang School of Physical and Mathematical Sciences Empirical Likelihood Large Dimensional Data DRNTU::Science::Mathematics The empirical likelihood is a versatile nonparametric approach to testing hypotheses and constructing confidence regions. However it is not clear if Wilks’ Theorem still works in high dimensions. In this paper, by adding two pseudo-observations to the original data set, we prove the asymptotic normality of the log empirical likelihood-ratio statistic when the sample size and the data dimension are comparable. In practice, we suggest using the normalized F(p,n-p) distribution to approximate its distribution. Simulation results show excellent performance of this approximation. 2018-12-07T07:34:54Z 2019-12-06T16:54:27Z 2018-12-07T07:34:54Z 2019-12-06T16:54:27Z 2015 Journal Article Chen, B., Pan, G., Yang, Q., & Zhou, W. (2015). Large dimensional empirical likelihood. Statistica Sinica, 25, 1659-1677. doi:10.5705/ss.2013.246 1017-0405 https://hdl.handle.net/10356/88029 http://hdl.handle.net/10220/46882 10.5705/ss.2013.246 en Statistica Sinica © 2015 Statistica Sinica. |
| institution |
Nanyang Technological University |
| building |
NTU Library |
| country |
Singapore |
| collection |
DR-NTU |
| language |
English |
| topic |
Empirical Likelihood Large Dimensional Data DRNTU::Science::Mathematics |
| spellingShingle |
Empirical Likelihood Large Dimensional Data DRNTU::Science::Mathematics Chen, Binbin Pan, Guangming Yang, Qing Zhou, Wang Large dimensional empirical likelihood |
| description |
The empirical likelihood is a versatile nonparametric approach to testing hypotheses and constructing confidence regions. However it is not clear if Wilks’ Theorem still works in high dimensions. In this paper, by adding two pseudo-observations to the original data set, we prove the asymptotic normality of the log empirical likelihood-ratio statistic when the sample size and the data dimension are comparable. In practice, we suggest using the normalized F(p,n-p) distribution to approximate its distribution. Simulation results show excellent performance of this approximation. |
| author2 |
School of Physical and Mathematical Sciences |
| author_facet |
School of Physical and Mathematical Sciences Chen, Binbin Pan, Guangming Yang, Qing Zhou, Wang |
| format |
Article |
| author |
Chen, Binbin Pan, Guangming Yang, Qing Zhou, Wang |
| author_sort |
Chen, Binbin |
| title |
Large dimensional empirical likelihood |
| title_short |
Large dimensional empirical likelihood |
| title_full |
Large dimensional empirical likelihood |
| title_fullStr |
Large dimensional empirical likelihood |
| title_full_unstemmed |
Large dimensional empirical likelihood |
| title_sort |
large dimensional empirical likelihood |
| publishDate |
2018 |
| url |
https://hdl.handle.net/10356/88029 http://hdl.handle.net/10220/46882 |
| _version_ |
1681034521211830272 |