Article View/Open
Publication Export
Related Publications in TAIR
- > Simple Record
- > Full Record
| Field |
Value |
| Title: | Filtered-variate prior distributions for histograms smoothing |
| Authors: | Jiang, Thomas J.
姜志銘
Dickey, James M. |
| Contributors: | 應數系 |
| Keywords: | Bayesian smoothing ;
Carlson function ;
Generalized Dirichlet distribution ;
Generalized hypergeometric function ;
Multinomial distribution ;
Multinomial estimation |
| Date: | 1998-06 |
| Issue Date: | 2008-12-24 13:29:01 (UTC+8) |
| Abstract: | We develop prior distributions for histogram inference favoring smooth population frequencies; that is, probability vectors with small differences for neighboring categories. We give a theory of prior-random probability vectors representable as a linear transform, or “filter,” of a standard random probability vector, or equivalently, a random weighted average of nonrandom smooth probability vectors. Promising methods of prior assessment are given based on elicitation of a list of typically smooth probability vectors, the empirical moments of which can then be matched by the mean vector and variance matrix of a constructed continuous-type filtered-variate prior distribution. |
| Relation: | Journal of the American Statistical Association,93,651-662 |
| Data Type: | article |
| DOI: | http://dx.doi.org/10.1080/01621459.1998.10473718 |
| DCField |
Value |
Language |
| dc.contributor (Contributor) | 應數系 | - |
| dc.creator (Authors) | Jiang, Thomas J. | en_US |
| dc.creator (Authors) | 姜志銘 | - |
| dc.creator (Authors) | Dickey, James M. | en_US |
| dc.date (Date) | 1998-06 | en_US |
| dc.date.accessioned | 2008-12-24 13:29:01 (UTC+8) | - |
| dc.date.available | 2008-12-24 13:29:01 (UTC+8) | - |
| dc.date.issued (Issue Date) | 2008-12-24 13:29:01 (UTC+8) | - |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/18685 | - |
| dc.description.abstract (Abstract) | We develop prior distributions for histogram inference favoring smooth population frequencies; that is, probability vectors with small differences for neighboring categories. We give a theory of prior-random probability vectors representable as a linear transform, or “filter,” of a standard random probability vector, or equivalently, a random weighted average of nonrandom smooth probability vectors. Promising methods of prior assessment are given based on elicitation of a list of typically smooth probability vectors, the empirical moments of which can then be matched by the mean vector and variance matrix of a constructed continuous-type filtered-variate prior distribution. | - |
| dc.format | application/ | en_US |
| dc.language (Language) | en | en_US |
| dc.language (Language) | en-US | en_US |
| dc.language.iso | en_US | - |
| dc.relation (Relation) | Journal of the American Statistical Association,93,651-662 | en_US |
| dc.subject (Keywords) | Bayesian smoothing ;
Carlson function ;
Generalized Dirichlet distribution ;
Generalized hypergeometric function ;
Multinomial distribution ;
Multinomial estimation | - |
| dc.title (Title) | Filtered-variate prior distributions for histograms smoothing | en_US |
| dc.type (Data Type) | article | en |
| dc.identifier.doi (DOI) | 10.1080/01621459.1998.10473718 | - |
| dc.doi.uri | http://dx.doi.org/10.1080/01621459.1998.10473718 | - |
(369)