Empirical likelihood confidence intervals for nonparametric functional data analysis
We consider the problem of constructing confidence intervals for nonparametric functional data analysis using empirical likelihood. In this doubly infinite-dimensional context, we demonstrate the Wilk's phenomenon and propose a bias-corrected construction that requires neither undersmoothing no...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Online Access: | https://hdl.handle.net/10356/99370 http://hdl.handle.net/10220/17246 |
| _version_ | 1826124367427272704 |
|---|---|
| author | Lian, Heng |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences Lian, Heng |
| author_sort | Lian, Heng |
| collection | NTU |
| description | We consider the problem of constructing confidence intervals for nonparametric functional data analysis using empirical likelihood. In this doubly infinite-dimensional context, we demonstrate the Wilk's phenomenon and propose a bias-corrected construction that requires neither undersmoothing nor direct bias estimation. We also extend our results to partially linear regression models involving functional data. Our numerical results demonstrate improved performance of the empirical likelihood methods over normal approximation-based methods. |
| first_indexed | 2024-10-01T06:19:29Z |
| format | Journal Article |
| id | ntu-10356/99370 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:19:29Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/993702020-03-07T12:37:17Z Empirical likelihood confidence intervals for nonparametric functional data analysis Lian, Heng School of Physical and Mathematical Sciences We consider the problem of constructing confidence intervals for nonparametric functional data analysis using empirical likelihood. In this doubly infinite-dimensional context, we demonstrate the Wilk's phenomenon and propose a bias-corrected construction that requires neither undersmoothing nor direct bias estimation. We also extend our results to partially linear regression models involving functional data. Our numerical results demonstrate improved performance of the empirical likelihood methods over normal approximation-based methods. 2013-11-05T04:36:33Z 2019-12-06T20:06:31Z 2013-11-05T04:36:33Z 2019-12-06T20:06:31Z 2012 2012 Journal Article Lian, H. (2012). Empirical likelihood confidence intervals for nonparametric functional data analysis. Journal of Statistical Planning and Inference, 142(7), 1669-1677. 0378-3758 https://hdl.handle.net/10356/99370 http://hdl.handle.net/10220/17246 10.1016/j.jspi.2012.02.008 en Journal of statistical planning and inference |
| spellingShingle | Lian, Heng Empirical likelihood confidence intervals for nonparametric functional data analysis |
| title | Empirical likelihood confidence intervals for nonparametric functional data analysis |
| title_full | Empirical likelihood confidence intervals for nonparametric functional data analysis |
| title_fullStr | Empirical likelihood confidence intervals for nonparametric functional data analysis |
| title_full_unstemmed | Empirical likelihood confidence intervals for nonparametric functional data analysis |
| title_short | Empirical likelihood confidence intervals for nonparametric functional data analysis |
| title_sort | empirical likelihood confidence intervals for nonparametric functional data analysis |
| url | https://hdl.handle.net/10356/99370 http://hdl.handle.net/10220/17246 |
| work_keys_str_mv | AT lianheng empiricallikelihoodconfidenceintervalsfornonparametricfunctionaldataanalysis |