Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions
This paper discusses the asymptotic covariance and outlier detection procedure in a linear functional relationship model for an extended circular model proposed by Caires and Wyatt. We derive the asymptotic covariance matrix of the model via the Fisher information and use the results to detect influ...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Thailands Natl Science & Technology Development Agency
2010
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/12507/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1831448525769015296 |
|---|---|
| author | Hussin, A.G. Abuzaid, A. Zulkifili, F. Mohamed, I. |
| author_facet | Hussin, A.G. Abuzaid, A. Zulkifili, F. Mohamed, I. |
| author_sort | Hussin, A.G. |
| building | UM Library |
| collection | Institutional Repository |
| content_provider | Universiti Malaya |
| content_source | UM Research Repository |
| continent | Asia |
| country | Malaysia |
| description | This paper discusses the asymptotic covariance and outlier detection procedure in a linear functional relationship model for an extended circular model proposed by Caires and Wyatt. We derive the asymptotic covariance matrix of the model via the Fisher information and use the results to detect influential observations in the model. Consequently, an influential observation detection procedure is developed based on the COVRATIO statistic which has been widely used for similar purposes in ordinary linear regression models. We show via simulation that the above procedure performs well in detecting influential observations. As an illustration, the procedure is applied to the real data of the wind direction measured by two different instruments. |
| format | Article |
| id | my.um.eprints-12507 |
| institution | Universiti Malaya |
| publishDate | 2010 |
| publisher | Thailands Natl Science & Technology Development Agency |
| record_format | eprints |
| spelling | my.um.eprints-125072015-01-30T03:06:26Z http://eprints.um.edu.my/12507/ Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions Hussin, A.G. Abuzaid, A. Zulkifili, F. Mohamed, I. R Medicine This paper discusses the asymptotic covariance and outlier detection procedure in a linear functional relationship model for an extended circular model proposed by Caires and Wyatt. We derive the asymptotic covariance matrix of the model via the Fisher information and use the results to detect influential observations in the model. Consequently, an influential observation detection procedure is developed based on the COVRATIO statistic which has been widely used for similar purposes in ordinary linear regression models. We show via simulation that the above procedure performs well in detecting influential observations. As an illustration, the procedure is applied to the real data of the wind direction measured by two different instruments. Thailands Natl Science & Technology Development Agency 2010 Article PeerReviewed Hussin, A.G. and Abuzaid, A. and Zulkifili, F. and Mohamed, I. (2010) Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions. Scienceasia, 36 (3). pp. 249-253. |
| spellingShingle | R Medicine Hussin, A.G. Abuzaid, A. Zulkifili, F. Mohamed, I. Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| title | Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| title_full | Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| title_fullStr | Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| title_full_unstemmed | Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| title_short | Asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| title_sort | asymptotic covariance and detection of influential observations in a linear functional relationship model for circular data with application to the measurements of wind directions |
| topic | R Medicine |
| url | http://eprints.um.edu.my/12507/ |
| url_provider | http://eprints.um.edu.my/ |