𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Modeling Probabilistic Networks of Discrete and Continuous Variables

✍ Scribed by Enrique Castillo; José Manuel Gutiérrez; Ali S. Hadi

Publisher
Elsevier Science
Year
1998
Tongue
English
Weight
378 KB
Volume
64
Category
Article
ISSN
0047-259X

No coin nor oath required. For personal study only.

✦ Synopsis

In this paper we show how discrete and continuous variables can be combined using parametric conditional families of distributions and how the likelihood weighting method can be used for propagating uncertainty through the network in an efficient manner. To illustrate the method we use, as an example, the damage assessment of reinforced concrete structures of buildings and we formalize the steps to be followed when modeling probabilistic networks. We start with one set of conditional probabilities. Then, we examine this set for uniqueness, consistency, and parsimony. We also show that cycles can be removed because they lead to redundant probability information. This redundancy may cause inconsistency, hence the probabilities must be checked for consistency. This examination may require a reduction to an equivalent set in standard canonical form from which one can always construct a Bayesian network, which is the most convenient model. We also perform a sensitivity analysis, which shows that the model is robust.

📜 SIMILAR VOLUMES

Entropy and MDL discretization of contin
Entropy and MDL discretization of continuous variables for Bayesian belief networks
✍ Ellis J. Clarke; Bruce A. Barton 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 313 KB 👁 2 views

An efficient algorithm for partitioning the range of a continuous variable to a discrete Ž . number of intervals, for use in the construction of Bayesian belief networks BBNs , is presented here. The partitioning minimizes the information loss, relative to the number of intervals used to represent t

Covariance Adjustments in Discrimination
Covariance Adjustments in Discrimination of Mixed Discrete and Continuous Variables
✍ Chi-Ying Leung 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 126 KB

Sufficient conditions are given to ensure a better performance of the plug-in version of the covariates adjusted location linear discriminant function in an asymptotic comparison of the overall expected error rate. Our findings generalize several earlier results on discriminant function with covaria

Maximum entropy inference for mixed cont
Maximum entropy inference for mixed continuous-discrete variables
✍ Hermann Singer 📂 Article 📅 2010 🏛 John Wiley and Sons 🌐 English ⚖ 266 KB

We represent knowledge by probability distributions of mixed continuous and discrete variables. From the joint distribution of all items, one can compute arbitrary conditional distributions, which may be used for prediction. However, in many cases only some marginal distributions, inverse probabilit

Nearest Neighbor Classification Rule for
Nearest Neighbor Classification Rule for Mixtures of Discrete and Continuous Random Variables
✍ T. J. Wojciechowski 📂 Article 📅 1987 🏛 John Wiley and Sons 🌐 English ⚖ 297 KB 👁 2 views

In this paper very simple nonparametric c l d i c a t i o n rule for mixtures of discrete and oonhuons random variables is described. It ie based on the method of neatest neighbor proposed by COVEB and HABT (1967). The bounds on the limit of the near& neighbor ruleriske are given. Both lower and upp

The Empirical Bayes Classification Rules
The Empirical Bayes Classification Rules for Mixtures of Discrete and Continuous Variables
✍ T. Wojciechowski 📂 Article 📅 1985 🏛 John Wiley and Sons 🌐 English ⚖ 603 KB

Let us consider a general population R. Each object belonging to the population R is characterized by a pair of correlated random vectors (& I). Both X and \_Y may be mixtures of discrete and continuous random variables. It will be assumed that our population R consists of k groups nl, ..., 3zk, whi