A probabilistic method of reasoning under uncertainty is proposed based on the principle of Minimum Cross Entropy (MCE) and concept of Recursive Causal Model (RCM). The dependency and correlations among the variables are described in a special language BNDL (Belief Networks Description Language). Beliefs are propagated among the clauses of the BNDL programs representing the underlying probabili...

Multiply sectioned Bayesian networks for single-agent systems are extended into a framework for cooperative multi-agent distributed interpretation systems. Each agent is represented as a Bayesian subnet. We show that the semantics of the joint probability distribution of such a system is well defined under reasonable conditions. Unlike in single-agent systems where evidence is entered one subne...

Semi-Markovian causal models (SMCMs) are an extension of causal Bayesian networks for modeling problems with latent variables. However, there is a big gap between the SMCMs used in theoretical studies and the models that can be learned from observational data alone. The result of standard algorithms for learning from observations, is a complete partially ancestral graph (CPAG), representing the...

One of the important aspects of human causal reasoning is that from the time we are young children we reason about unobserved causes. How can we learn about unobserved causes from information about observed events? Causal Bayes nets provide a formal account of how causal structure is learned from a combination of associations and interventions. This formalism makes specific predictions about th...

Maier et al. (2010) introduced the relational causal model (RCM) for representing and inferring causal relationships in relational data. A lifted representation, called abstract ground graph (AGG), plays a central role in reasoning with and learning of RCM. The correctness of the algorithm proposed by Maier et al. (2013a) for learning RCM from data relies on the soundness and completeness of AG...

The validity of a causal model can be tested only if the model imposes constraints on the probability distribution that governs the gen­ erated data. In the presence of unmeasured variables, causal models may impose two types of constraints: conditional independen­ cies, as read through the d-separation crite­ rion, and functional constraints, for which no general criterion is available. This p...

In this paper we describe ADMIT, a software application developed to assist the graduate admissions process at the University of Pittsburgh School of Information Sciences (SIS). ADMIT uses a Bayesian network model built from historical admissions data and academic performance records to predict how likely each applicant is to succeed. The system rank-orders applicants based on the probability o...

Augmenting the graphoid axioms with three additional rules enables us to handle independencies among observed as well as counterfactual variables. The augmented set of axioms facilitates the derivation of testable implications and ignorability conditions whenever modeling assumptions are articulated in the language of counterfactuals. 1 Motivation Consider the causal Markov chain X → Y → Z whic...

The approximate Bayesian bootstrap is suggested by Rubin & Schenker (1986) as a way of generating multiple imputations when the original sample can be regarded as independently and identically distributed and the response mechanism is ignorable. We investigate the finite sample properties of the variance estimator when the approximate Bayesian bootstrap method is used and show that the bias is ...

Hidden variables are well known sources of disturbance when recovering belief networks from data based only on measurable variables. Hence models assuming existence of hidden variables are under development. This paper presents a new algorithm ”accelerating” the known CI algorithm of Spirtes, Glymour and Scheines [20]. We prove that this algorithm does not produces (conditional) independencies ...