Smith, J.Q. and Queen, C.M. (1996) Bayesian models for sparse probability tables. Annals of Statistics, 24 (5). pp. 2178-2198. ISSN 0090-5364.
|The full text of this publication is not available from this repository. (Contact us about this Publication)|
We wish to make inferences about the conditional probabilities p(y/x), many of which are zero, when the distribution of X is unknown and one observes only a multinomial sample of the Y variates. To do this, fixed likelihood ratio models and quasi-incremental distributions are defined. It is shown that quasi-incremental distributions are intimately linked to decomposable graphs and that these graphs can guide us to transformations of X and Y which admit a conjugate Bayesian analysis on a reparametrization of the conditional probabilities of interest.
|Uncontrolled keywords:||Bayesian probability estimation; constraint graph; contingency tables; decomposable graph; generalized Dirichlet distributions; separation of likelihood|
|Subjects:||H Social Sciences > HA Statistics|
|Divisions:||Faculties > Science Technology and Medical Studies > School of Mathematics Statistics and Actuarial Science > Statistics|
|Depositing User:||P. Ogbuji|
|Date Deposited:||27 May 2009 08:05|
|Last Modified:||17 Jul 2012 10:20|
|Resource URI:||http://kar.kent.ac.uk/id/eprint/18509 (The current URI for this page, for reference purposes)|
- Depositors only (login required):