A Simple Constraint-Based Algorithm for Efficiently Mining Observational Databases for Causal Relationships

This paper presents a simple, efficient computer-based method for discovering causal relationships from databases that contain observational data. Observational data is passively observed, as contrasted with experimental data. Most of the databases available for data mining are observational. There is great potential for mining such databases to discover causal relationships. We illustrate how observational data can constrain the causal relationships among measured variables, sometimes to the point that we can conclude that one variable is causing another variable. The presentation here is based on a constraint-based approach to causal discovery. A primary purpose of this paper is to present the constraint-based causal discovery method in the simplest possible fashion in order to (1) readily convey the basic ideas that underlie more complex constraint-based causal discovery techniques, and (2) permit interested readers to rapidly program and apply the method to their own databases, as a start toward using more elaborate causal discovery algorithms.     

Finances and Well-Being: A Dynamic Equilibrium Model of Resources.

This study of 513 Dutch farmers tested a dynamic equilibrium model of resources (an extension of the conservation of resources theory; S. E. Hobfoll, 1989, 1998, 2001). With structural equation modeling, the advantages of a 3-wave longitudinal design were comprehensively used, such as addressing bidirectional causal effects and within-individual vs. between-individual change. This allowed for a careful analysis of the management function of resources in the stress process. Results showed that well-being had stronger within-person stability than finances. Increased levels of financial problems temporarily increased psychological distress but not self-reported illness. Conversely, farmers with higher stable baselines of psychological distress also had higher baselines of self-reported illness and experienced more negative changes in their financial situation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Casual reasoning in planning1

Reasoning about actions necessarily involves tracking the truth of assertions about the world over time. The SIPE planning system retains the efficiency of the STRIPS assumption for this while enhancing expressive power by allowing the specification of a causl theory. Separation of knowledge about causality from knowledge about actions relieves operators of much of their representational burden and allows them to be applicable in a wide range of contexts. The implementation of causal theories is described, together with examples and evaluations of the system's expressive power and efficiency.     

Integrating integer programming and probabilistic deduction graphs for probabilistic reasoning

Optimal solutions of several variants of the probabilistic reasoning problem were found by a new technique that integrates integer programming and probabilistic deduction graphs (PDG). PDGs are extended from deduction graphs of the and-type via normal deduction graphs. The foregoing variants to be solved can involve multiple hypotheses and multiple evidences where the former is given and the latter is unknown and being found or vice versa. The relationship among these hypotheses and evidences with possible intermediaries is represented by a causal graph. The proposed method can handle a large causal graph of any type and find an optimal solution by invoking a linear integer programming package. In addition, formulating the reasoning problem to fit integer programming takes a polynomial time. H.-L. Li was visiting the Department of Computer Sciences, University of North Texas in 1988–1989. He is with the Institute of Information Management, National Chiao Tung University, Hsinchu, Taiwan, R.O.C.     

Does the alliance cause good outcome? Recommendations for future research on the alliance.

Research has consistently documented that the quality of the therapeutic alliance is related to the outcome of diverse psychotherapies. Insufficient attention, however, has been directed at identifying the nature and magnitude of the causal relationship between the alliance and outcome. In this commentary, we discuss the major threats to causal interpretation of alliance-outcome correlations and provide suggestions for future research that would help clarify the extent to which the alliance causes positive outcomes. Assuming the alliance is a causal factor in relation to outcome, we provide recommendations for research on the alliance that would attempt to improve patient care by enhancing the alliance. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Can being scared cause tummy aches? Naive theories, ambiguous evidence, and preschoolers' causal inferences.

Causal learning requires integrating constraints provided by domain-specific theories with domain-general statistical learning. In order to investigate the interaction between these factors, the authors presented preschoolers with stories pitting their existing theories against statistical evidence. Each child heard 2 stories in which 2 candidate causes co-occurred with an effect. Evidence was presented in the form: AB→E; CA→E; AD→E; and so forth. In 1 story, all variables came from the same domain; in the other, the recurring candidate cause, A, came from a different domain (A was a psychological cause of a biological effect). After receiving this statistical evidence, children were asked to identify the cause of the effect on a new trial. Consistent with the predictions of a Bayesian model, all children were more likely to identify A as the cause within domains than across domains. Whereas 3.5-year-olds learned only from the within-domain evidence, 4- and 5-year-olds learned from the cross-domain evidence and were able to transfer their new expectations about psychosomatic causality to a novel task. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

一种DVE中通用的因果消息序时间管理分布式中间件

对于遵循高层体系结构(HLA)标准构建的分布式虚拟环境(DVE),时间管理服务的性能将直接影响分布式仿真的效率和正确性。目前的时间管理服务实现了两种消息排序机制:接收序和时戳序。接收序对消息按其接收顺序进行处理,实时性高,但无法正确处理接收顺序与产生顺序相违背的消息;时戳序通常指保守时戳序机制,能对消息按其产生的时间顺序进行处理,但时间开销较大,难以到达DVE的实时性要求。因此,本文以分布式中间件的方式为DVE设计实现了一种因果消息序时间管理服务,提供符合HLA标准的程序接口,使分布式仿真应用在不改变原有调用接口的情况下,能够通过中间件对消息实现因果序时间管理。实验表明,使用该中间件可以有效维护消息的处理顺序,同时时间开销小,能够较好地满足DVE的实时性要求。     

A review of the use of human factors classification frameworks that identify causal factors for adverse events in the hospital setting

Various human factors classification frameworks have been used to identified causal factors for clinical adverse events. A systematic review was conducted to identify human factors classification frameworks that identified the causal factors (including human error) of adverse events in a hospital setting. Six electronic databases were searched, identifying 1997 articles and 38 of these met inclusion criteria. Most studies included causal contributing factors as well as error and error type, but the nature of coding varied considerably between studies. The ability of human factors classification frameworks to provide information on specific causal factors for an adverse event enables the focus of preventive attention on areas where improvements are most needed. This review highlighted some areas needing considerable improvement in order to meet this need, including better definition of terms, more emphasis on assessing reliability of coding and greater sophistication in analysis of results of the classification.

Practitioner Summary: Human factors classification frameworks can be used to identify causal factors of clinical adverse events. However, this review suggests that existing frameworks are diverse, limited in their identification of the context of human error and have poor reliability when used by different individuals.     

Anticipatory network models of multicriteria decision-making processes

In this article, we will investigate the properties of a compromise solution selection method based on modelling the consequences of a decision as factors influencing the decision making in subsequent problems. Specifically, we assume that the constraints and preference structures in the (k?+?1)st multicriteria optimisation problem depend on the values of criteria in the k-th problem. To make a decision in the initial problem, the decision maker should take into account the anticipated outcomes of each linked future decision problem. This model can be extended to a network of linked decision problems, such that causal relations are defined between the time-ordered nodes. Multiple edges starting from a decision node correspond to different future scenarios of consequences at this node. In addition, we will define the relation of anticipatory feedback, assuming that some decision makers take into account the anticipated future consequences of their decisions described by a network of optimisers ? a class of information processing units introduced in this article. Both relations (causal and anticipatory) form a feedback information model, which makes possible a selection of compromise solutions taking into account the anticipated consequences. We provide constructive algorithms to solve discrete multicriteria decision problems that admit the above preference information structure. An illustrative example is presented in Section 4. Various applications of the above model, including the construction of technology foresight scenarios, are discussed in the final section of this article.