Article View/Open
Publication Export
|
|
| No doi shows Citation Infomation |
Related Publications in TAIR
- > Simple Record
- > Full Record
| Field |
Value |
| Title: | Comptability of finite discrete conditional distributions. |
| Authors: | Song, Chwan-Chin;Li, Lung-An;Chen, Chong-Hong;Jiang, Thomas J.;Kuo, Kun-Lin
宋傳欽
Song, Chwan-Chin
姜志銘
Jiang, Thomas J. |
| Contributors: | 應數系 |
| Keywords: | Compatibility; conditional density; irreducible block diagonal matrix; joint density; marginal density; rank one positive extension matrix; ratio matrix; uniqueness. |
| Date: | 2010 |
| Issue Date: | 2018-09-27 17:17:21 (UTC+8) |
| Abstract: | This paper provides new versions of necessary and sufficient conditions for compatibility of finite discrete conditional distributions, and of the uniqueness for those compatible conditional distributions. We note that the ratio matrix (the matrix $C$ in Arnold and Press (1989)), after interchanging its rows and/or columns, can be rearranged to be an irreducible block diagonal matrix. We find that checking compatibility is equivalent to inspecting whether every block on the diagonal has a rank one positive extension, and that the necessary and sufficient conditions of the uniqueness, if the given conditional densities are compatible, is that the ratio matrix itself is irreducible. We show that each joint density, if it exists, corresponds to a rank one positive extension of the ratio matrix, and we characterize the set of all possible joint densities. Finally, we provide algorithms for checking compatibility, for checking uniqueness, and for constructing densities. |
| Relation: | Statistica Sinica, 20 (2010), 423-440 |
| Data Type: | article |
| DCField |
Value |
Language |
| dc.contributor (Contributor) | 應數系 | |
| dc.creator (Authors) | Song, Chwan-Chin;Li, Lung-An;Chen, Chong-Hong;Jiang, Thomas J.;Kuo, Kun-Lin | |
| dc.creator (Authors) | 宋傳欽 | |
| dc.creator (Authors) | Song, Chwan-Chin | |
| dc.creator (Authors) | 姜志銘 | |
| dc.creator (Authors) | Jiang, Thomas J. | |
| dc.date (Date) | 2010 | |
| dc.date.accessioned | 2018-09-27 17:17:21 (UTC+8) | - |
| dc.date.available | 2018-09-27 17:17:21 (UTC+8) | - |
| dc.date.issued (Issue Date) | 2018-09-27 17:17:21 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/120182 | - |
| dc.description.abstract (Abstract) | This paper provides new versions of necessary and sufficient conditions for compatibility of finite discrete conditional distributions, and of the uniqueness for those compatible conditional distributions. We note that the ratio matrix (the matrix $C$ in Arnold and Press (1989)), after interchanging its rows and/or columns, can be rearranged to be an irreducible block diagonal matrix. We find that checking compatibility is equivalent to inspecting whether every block on the diagonal has a rank one positive extension, and that the necessary and sufficient conditions of the uniqueness, if the given conditional densities are compatible, is that the ratio matrix itself is irreducible. We show that each joint density, if it exists, corresponds to a rank one positive extension of the ratio matrix, and we characterize the set of all possible joint densities. Finally, we provide algorithms for checking compatibility, for checking uniqueness, and for constructing densities. | en_US |
| dc.format.extent | 178927 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (Relation) | Statistica Sinica, 20 (2010), 423-440 | |
| dc.subject (Keywords) | Compatibility; conditional density; irreducible block diagonal matrix; joint density; marginal density; rank one positive extension matrix; ratio matrix; uniqueness. | |
| dc.title (Title) | Comptability of finite discrete conditional distributions. | |
| dc.type (Data Type) | article | |
(166)