By applying the minimality principle for model selection, one should seek the model that describes the data by a code of minimal length. Learning is viewed as data compression that exploits the regularities or qualitative properties found in the data, in order to build a model containing the meaningful information. The theory of causal modeling can be interpreted by this approach. The regularit...

Association between two variables may be reversed by marginalizing over another possibly unobserved background. This reversal is called the Yule-Simpson paradox (Yule, 1903; Simpson, 1951). To avoid the reversal, many authors discussed collapsibility of association measures over a background (Wermuth, 1987; Geng, 1992; Cox and Wermuth, 2003). Causal effects and relationships among variables may...

Causality analytic techniques based on conditional mutual information are described. Causality analysis may be used to infer linear and nonlinear causal relations between selected brain regions, and can account for identified non-causal confounds. The analysis results in a directed graph whose nodes are brain regions, and whose edges represent information flow. This causal information measure i...

Bayesian methods have been developed for learning Bayesian networks from data. Most of this work has concentrated on Bayesian networks interpreted as a representation of probabilistic conditional independence without considering causation. Other researchers have shown that having a causal interpretation can be important, because it allows us to predict the effects of interventions in a domain. ...

Causal manipulation theorems proposed by Spirtes et al. in the context of directed probabilistic graphs, such as Bayesian networks, do not model so called reversible causal mechanisms, i.e., mechanisms that are capable of working in several directions, depending on which of their variables are manipulated exogenously. An example involving reversible causal mechanisms is the power train of a car...

The construction of causal graphs from non-experimental data rests on a set of constraints that the graph structure imposes on all probability distributions compatible with the graph. These constraints are of two types: conditional independencies and algebraic constraints, first noted by Verma. While conditional independencies are well studied and frequently used in causal induction algorithms,...

Available evidence indicates that responses to conditional inferences using concrete causal premises is affected by the relative number of available alternate causes (Cummins, D.D., 1995. Memory and Cognition 23 (5), 646-658). We propose that another important factor that may influence the kinds of inferences made to causal conditionals is the relative strength of association between such cause...

We extend the 0-approximation of sensing actions and incomplete information in (Son and Baral 2001) to action theories with static causal laws and prove its soundness with respect to the possible world semantics. We also show that the conditional planning problem with respect to this approximation is NP-complete. We then present an answer set programming based conditional planner, called ASCP, ...

This paper analyses three Granger noncausality hypotheses within a conditionally Gaussian MS-VAR model. Noncausality in mean is based on Granger’s original concept for linear predictors by defining noncausality from the 1-step ahead forecast error variance for the conditional expectation. Noncausality in mean-variance concerns the conditional forecast error variance, while noncausality in distr...

The Elephant in the Corner: A Cautionary Tale about Measurement Error in Treatment Effects Models Researchers in economics and other disciplines are often interested in the causal effect of a binary treatment on outcomes. Econometric methods used to estimate such effects are divided into one of two strands depending on whether they require the conditional independence assumption (i.e., independ...