Bayesian Analysis in Expert Systems
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Bayesian Analysis in Expert Systems. / SPIEGELHALTER, DJ; DAWID, AP; Lauritzen, Steffen L.; COWELL, RG.
In: Statistical Science, Vol. 8, No. 3, 1993, p. 219-247.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Bayesian Analysis in Expert Systems
AU - SPIEGELHALTER, DJ
AU - DAWID, AP
AU - Lauritzen, Steffen L.
AU - COWELL, RG
PY - 1993
Y1 - 1993
N2 - We review recent developments in applying Bayesian probabilistic and statistical ideas to expert systems. Using a real, moderately complex, medical example we illustrate how qualitative and quantitative knowledge can be represented within a directed graphical model, generally known as a belief network in this context. Exact probabilistic inference on individual cases is possible using a general propagation procedure. When data on a series of cases are available, Bayesian statistical techniques can be used for updating the original subjective quantitative inputs, and we present a set of diagnostics for identifying conflicts between the data and the prior specification. A model comparison procedure is explored, and a number of links made with mainstream statistical methods. Details are given on the use of Dirichlet prior distributions for learning about parameters and the process of transforming the original graphical model to a junction tree as the basis for efficient computation.
AB - We review recent developments in applying Bayesian probabilistic and statistical ideas to expert systems. Using a real, moderately complex, medical example we illustrate how qualitative and quantitative knowledge can be represented within a directed graphical model, generally known as a belief network in this context. Exact probabilistic inference on individual cases is possible using a general propagation procedure. When data on a series of cases are available, Bayesian statistical techniques can be used for updating the original subjective quantitative inputs, and we present a set of diagnostics for identifying conflicts between the data and the prior specification. A model comparison procedure is explored, and a number of links made with mainstream statistical methods. Details are given on the use of Dirichlet prior distributions for learning about parameters and the process of transforming the original graphical model to a junction tree as the basis for efficient computation.
U2 - 10.1214/ss/1177010888
DO - 10.1214/ss/1177010888
M3 - Journal article
VL - 8
SP - 219
EP - 247
JO - Statistical Science
JF - Statistical Science
SN - 0883-4237
IS - 3
ER -
ID: 128007334