Results 1 
8 of
8
Blocking Gibbs Sampling in Very Large Probabilistic Expert Systems
 Internat. J. Human–Computer Studies
, 1995
"... We introduce a methodology for performing approximate computations in very complex probabilistic systems (e.g. huge pedigrees). Our approach, called blocking Gibbs, combines exact local computations with Gibbs sampling in a way that complements the strengths of both. The methodology is illustrate ..."
Abstract

Cited by 46 (0 self)
 Add to MetaCart
We introduce a methodology for performing approximate computations in very complex probabilistic systems (e.g. huge pedigrees). Our approach, called blocking Gibbs, combines exact local computations with Gibbs sampling in a way that complements the strengths of both. The methodology is illustrated on a realworld problem involving a heavily inbred pedigree containing 20;000 individuals. We present results showing that blockingGibbs sampling converges much faster than plain Gibbs sampling for very complex problems.
Blocking Gibbs Sampling for Linkage Analysis in Large Pedigrees with Many Loops
 AMERICAN JOURNAL OF HUMAN GENETICS
, 1996
"... We will apply the method of blocking Gibbs sampling to a problem of great importance and complexity  linkage analysis. Blocking Gibbs combines exact local computations with Gibbs sampling in a way that complements the strengths of both. The method is able to handle problems with very high complexi ..."
Abstract

Cited by 24 (2 self)
 Add to MetaCart
We will apply the method of blocking Gibbs sampling to a problem of great importance and complexity  linkage analysis. Blocking Gibbs combines exact local computations with Gibbs sampling in a way that complements the strengths of both. The method is able to handle problems with very high complexity such as linkage analysis in large pedigrees with many loops; a task that no other known method is able to handle. New developments of the method are outlined, and it is applied to a highly complex linkage problem.
Nested Junction Trees
 In Proc. 13th Conf. on Uncertainty in Artificial Intelligence
, 1997
"... The efficiency of inference in both the Hugin and, most notably, the ShaferShenoy architectures can be improved by exploiting the independence relations induced by the incoming messages of a clique. That is, the message to be sent from a clique can be computed via a factorization of the clique pote ..."
Abstract
 Add to MetaCart
The efficiency of inference in both the Hugin and, most notably, the ShaferShenoy architectures can be improved by exploiting the independence relations induced by the incoming messages of a clique. That is, the message to be sent from a clique can be computed via a factorization of the clique potential in the form of a junction tree. In this paper we show that by exploiting such nested junction trees in the computation of messages both space and time costs of the conventional propagation methods may be reduced. The paper presents a structured way of exploiting the nested junction trees technique to achieve such reductions. The usefulness of the method is emphasized through a thorough empirical evaluation involving ten large realworld Bayesian networks and the Hugin inference algorithm. 1 INTRODUCTION Inference in Bayesian networks can be formulated as message passing in a junction tree corresponding to the network (Jensen, Lauritzen & Olesen 1990, Shafer & Shenoy 1990). More precis...
An Efficient Algorithm to Compute the Posterior Genotypic Distribution for Every Member of a Pedigree without Loops
, 1993
"... This paper describes a noniterative, recursive method to compute the likelihood for a pedigree without loops, and hence an efficient way to compute genotype probabilities for every member of the pedigree. The method can be used with multiple mates and large sibships. Scaling is used in calculations ..."
Abstract
 Add to MetaCart
This paper describes a noniterative, recursive method to compute the likelihood for a pedigree without loops, and hence an efficient way to compute genotype probabilities for every member of the pedigree. The method can be used with multiple mates and large sibships. Scaling is used in calculations to avoid numerical problems in working with large pedigrees.
Approved by: {<.c. ~
, 1981
"... (Under the direction of Robert C. Elston.) A multifactorial model for the segregation analysis of quantitative traits in pedigrees is presented. The model includes both polygenic and monogenic effects., The model also allows for two types of environmental correlation, a within sibship correlation an ..."
Abstract
 Add to MetaCart
(Under the direction of Robert C. Elston.) A multifactorial model for the segregation analysis of quantitative traits in pedigrees is presented. The model includes both polygenic and monogenic effects., The model also allows for two types of environmental correlation, a within sibship correlation and a within nuclear family correlation. Methods for the approximation of the true likelihood e for this model are presented. These models are derived from the methods for estimating the parameters of a mixture of normal distributions. The estimation methods are those equating moments, maximum likelihood and two methods of least squares estimation. One least squares method involves minimizing the sum of squared differences between the exact likelihood function and the approximation function; the
Institute of Statistics Mimeo Series No. 1408 July 1982MAXIMUM LIKELIHOOD METHODS FOR GENETIC ANALYSIS OF MULTIVARIATE PEDIGREE DATA
"... 1981 Approved by: /)r ..."
Blocking Gibbs Sampling in Very Large . . .
 INTERNATIONAL JOURNAL OF HUMAN COMPUTER STUDIES. SPECIAL ISSUE ON REALWORLD APPLICATIONS OF UNCERTAIN REASONING
, 1995
"... We introduce a methodology for performing approximate computations in very complex probabilistic systems (e.g. huge pedigrees). Our approach, called blocking Gibbs, combines exact local computations with Gibbs sampling in a way that complements the strengths of both. The methodology is illustrate ..."
Abstract
 Add to MetaCart
We introduce a methodology for performing approximate computations in very complex probabilistic systems (e.g. huge pedigrees). Our approach, called blocking Gibbs, combines exact local computations with Gibbs sampling in a way that complements the strengths of both. The methodology is illustrated on a realworld problem involving a heavily inbred pedigree containing 20;000 individuals. We present results showing that blockingGibbs sampling converges much faster than plain Gibbs sampling for very complex problems.