Strength Of Causal Relationships Research Articles

Root Cause Attribution of Delivery Risks via Causal Discovery with Reinforcement Learning

Managing delivery risks is a critical challenge in modern supply chain management due to the increasing complexity and interdependencies of global supply networks. Existing methods often rely on correlation-based approaches, which fail to uncover the true causes behind delivery delays. This limitation makes it difficult for supply chain managers to identify actionable factors that can mitigate risks effectively. To address these challenges, we propose a novel method that integrates causal discovery with reinforcement learning to identify the root causes of delivery risks. Unlike traditional correlation-based methods, our approach uncovers both the direction and strength of causal relationships between variables, allowing for more accurate identification of the key drivers behind delivery delays. By applying causal strength quantification, we further measure the impact of each factor on delivery performance. Using real-world supply chain data, our results demonstrate that the proposed method reveals hidden causal relationships between factors such as shipping mode, order size, and delivery status. These insights enable supply chain managers to implement more targeted interventions, significantly improving risk mitigation strategies.

A personal thermal comfort model based on causal artificial intelligence: a physiological sensor-enabled causal identifiability.

Personal thermal comfort affects occupants' health, well-being, and productivity. Its satisfaction is subjective, based on individual characteristics and dynamic environments, and challenging to understand, requiring predicted outcomes and explanations of how and why the outcomes happen. This research fulfills this concern using a personal thermal comfort model based on causal artificial intelligence. It encodes personal thermal comfort satisfaction based on a new causal-and-effect framework to connect the human mind and environmental factors. Random variables encode relevant factors, and the structural causal model performs cause-and-effect relationships. The do-calculus (e.g., d-separated and d-connected) draws the common sense of the model based on causal structure representation, contributing to a human-intelligent understanding. A directed acyclic graph and exact-inference-based variable elimination quantify the model parameters based on real-world observational data. The strength of causal relationships is verified based on causal odd ratio, causal sensitivity, and causal impact. The results highlight that our proposed model can encode physiological and physical factors to predict and explain personal thermal comfort satisfaction. It can predict and explain such satisfaction reasonably and robustly, converging to human-like interpretation. It can be applied to intelligent systems to understand personal thermal comfort.

Causal effects of plasma metabolites on chronic kidney diseases and renal function: a bidirectional Mendelian randomization study.

Despite the potential demonstrated by targeted plasma metabolite modulators in halting the progression of chronic kidney disease (CKD), a lingering uncertainty persists concerning the causal relationship between distinct plasma metabolites and the onset and progression of CKD. A genome-wide association study was conducted on 1,091 metabolites and 309 metabolite ratios derived from a cohort of 8,299 unrelated individuals of European descent. Employing a bidirectional two-sample Mendelian randomization (MR) analysis in conjunction with colocalization analysis, we systematically investigated the associations between these metabolites and three phenotypes: CKD, creatinine-estimated glomerular filtration rate (creatinine-eGFR), and urine albumin creatinine ratio (UACR). In the MR analysis, the primary analytical approach employed was inverse variance weighting (IVW), and sensitivity analysis was executed utilizing the MR-Egger method and MR-pleiotropy residual sum and outlier (MR-PRESSO). Heterogeneity was carefully evaluated through Cochrane's Q test. To ensure the robustness of our MR results, the leave-one-out method was implemented, and the strength of causal relationships was subjected to scrutiny via Bonferroni correction. Our thorough MR analysis involving 1,400 plasma metabolites and three clinical phenotypes yielded a discerning identification of 21 plasma metabolites significantly associated with diverse outcomes. Specifically, in the forward MR analysis, 6 plasma metabolites were determined to be causally associated with CKD, 16 with creatinine-eGFR, and 7 with UACR. Substantiated by robust evidence from colocalization analysis, 6 plasma metabolites shared causal variants with CKD, 16 with creatinine-eGFR, and 7 with UACR. In the reverse analysis, a diminished creatinine-eGFR was linked to elevated levels of nine plasma metabolites. Notably, no discernible associations were observed between other plasma metabolites and CKD, creatinine-eGFR, and UACR. Importantly, our analysis detected no evidence of horizontal pleiotropy. This study elucidates specific plasma metabolites causally associated with CKD and renal functions, providing potential targets for intervention. These findings contribute to an enriched understanding of the genetic underpinnings of CKD and renal functions, paving the way for precision medicine applications and therapeutic strategies aimed at impeding disease progression.

Causal relationship between gut microbiota and immune thrombocytopenia: a Mendelian randomization study of two samples.

Some observational studies have shown that immune thrombocytopenia (ITP) is highly associated with the alteration-composition of gut microbiota. However, the causality of gut microbiota on ITP has not yet been determined. Based on accessible summary statistics of the genome-wide union, the latent connection between ITP and gut microbiota was estimated using bi-directional Mendelian randomization (MR) and multivariable MR (MVMR) analyses. Inverse variance weighted (IVW), weighted median analyses, and MR-Egger regression methods were performed to examine the causal correlation between ITP and the gut microbiota. Several sensitivity analyses verified the MR results. The strength of causal relationships was evaluated using the MR-Steiger test. MVMR analysis was undertaken to test the independent causal effect. MR analyses of reverse direction were made to exclude the potential of reverse correlations. Finally, GO enrichment analyses were carried out to explore the biological functions. After FDR adjustment, two microbial taxa were identified to be causally associated with ITP (PFDR < 0.10), namely Alcaligenaceae (PFDR = 7.31 × 10-2) and Methanobacteriaceae (PFDR = 7.31 × 10-2). In addition, eight microbial taxa were considered as potentially causal features under the nominal significance (P < 0.05): Actinobacteria, Lachnospiraceae, Methanobacteria, Bacillales, Methanobacteriales, Coprococcus2, Gordonibacter, and Veillonella. According to the reverse-direction MR study findings, the gut microbiota was not significantly affected by ITP. There was no discernible horizontal pleiotropy or instrument heterogeneity. Finally, GO enrichment analyses showed how the identified microbial taxa participate in ITP through their underlying biological mechanisms. Several microbial taxa were discovered to be causally linked to ITP in this MR investigation. The findings improve our understanding of the gut microbiome in the risk of ITP.

Community perceptions of causes of violence against young women in Botswana: fuzzy cognitive mapping

ABSTRACT Violence against young women is a problem worldwide. Understanding its causes in a particular setting can inform context-specific interventions. We used Fuzzy cognitive mapping (FCM), a visual method for collating local knowledge about causes of health outcomes, to explore community views of factors that cause or prevent violence against young women in rural communities in southeast Botswana. In three communities, groups of young men, young women, older men, and older women built maps (68 participants and 12 maps in total) of factors they believed increased or decreased the risk of violence against young women. Trained local facilitators guided group sessions, drawing the reported factors as nodes linked by weighted arrows indicating the direction and strength of causal relationships among factors. Fuzzy transitive closure calculated the influence of each factor on others, considering direct and indirect connections. We combined maps by groups of stakeholders and condensed individual factors into categories which emerged from an inductive thematic analysis. The categories labelled conflict in relationships and parenting and family issues had the strongest influences on increasing violence across all maps. These categories were also common intermediaries between other causal categories and violence. The categories labelled women being disrespectful or uncooperative and transactional and intergenerational sex were the third and fourth strongest risk categories overall. Prominent protective concepts included a stronger legal framework and strengthening the role of local traditional leadership, with greater prominence on the maps of older participants. The most influential risk and protective categories were consistent across young men, young women, older men, and older women. FCM was feasible and acceptable with different stakeholders in Botswana. Fuzzy cognitive maps can inform community discussions, for example, of conflictive gender norms, family dynamics or healthier relationships, and are useful to build theories on how to act on the causes of violence against young women.

Productivity Growth Recovery Mechanisms: An ARDL Approach Lessons from the United States, Japan and South Korea

Productivity growth is an essential ingredient for achieving long-term economic growth and sustainable development. In the absence of such growth, economic growth is not achievable. Accordingly, this paper examines economic resilience through multiple productivity channels within the United States, Japan and South Korea. Adopting a Kaleckian post-Keynesian approach, productivity growth is constructed as a function of investment, capacity utilisation, indicators of financial development, and an indicator of fiscal policy. Utilising annual historical data from 1980-2019, this paper adopts Autoregressive Distributed Lag (ARDL) models, Vector Autoregressive-based Impulse Response Functions (IRF) and Variance Decompositions (VD) to examine the resilience of productivity growth through the speeds of adjustment after an external shock. Results show that long and short-run unidirectional causality between productivity growth and the explanatory variables exists amongst all economies through the errorcorrection terms (ECT) and ARDL models. When imposing a simulated one-time S.D. shock upon the explanatory variables, differing speeds of adjustment and recovery processes in the long-run are present. As such, the strength of causal relationships amongst productivity growth and the explanatory variables ultimately affects speeds of adjustment and hence recovery.

Identifying the Temporal Causal Relationship Between Alcohol and Tobacco Consumption with Aggregate Cancer Mortality over Alternative Time Horizons

Identifying the causal role of tobacco and alcohol has long been acknowledged as a critical area for developing preventative strategies in particular and public policy in general. This study utilizes a unique time series method in an effort to determine the strength of causal relationships between tobacco consumption, alcohol consumption and cancer mortality. By analysing tobacco expenditure, alcohol expenditure, while controlling for health expenditures and aggregate cancer data observed annually over an 80-year period fin the US population, we consider the relevant factors explaining and potentially guiding public health concerns going forward. Our results found that while tobacco and alcohol consumption (individually) causally impact cancer mortality, alcohol consumption maintains a stronger, bidirectional impact in comparison to tobacco consumption. From this, we consider explanations from an economic, biological and epidemiological front, gauging the strength of alcohol consumption on societal wellbeing. We find alcohol consumption to be a notable causal factor in cancer mortality that has been neglected from a public policy perspective in comparison to its more mediated tobacco counterpart.

Can statistical adjustment guided by causal inference improve the accuracy of effect estimation? A simulation and empirical research based on meta-analyses of case\u2013control studies

BackgroundStatistical adjustment is often considered to control confounding bias in observational studies, especially case–control studies. However, different adjustment strategies may affect the estimation of odds ratios (ORs), and in turn affect the results of their pooled analyses. Our study is aimed to investigate how to deal with the statistical adjustment in case–control studies to improve the validity of meta-analyses.MethodsThree types of adjustment strategies were evaluated including insufficient adjustment (not all preset confounders were adjusted), full adjustment (all confounders were adjusted under the guidance of causal inference), and improper adjustment (covariates other than confounders were adjusted). We carried out a series of Monte Carlo simulation experiments based on predesigned scenarios, and assessed the accuracy of effect estimations from meta-analyses of case–control studies by combining ORs calculated according to different adjustment strategies. Then we used the data from an empirical review to illustrate the replicability of the simulation results.ResultsFor all scenarios with different strength of causal relations, combining ORs that were comprehensively adjusted for confounders would get the most precise effect estimation. By contrast, combining ORs that were not sufficiently adjusted for confounders or improperly adjusted for mediators or colliders would easily introduce bias in causal interpretation, especially when the true effect of exposure on outcome was weak or none. The findings of the simulation experiments were further verified by the empirical research.ConclusionsStatistical adjustment guided by causal inference are recommended for effect estimation. Therefore, when conducting meta-analyses of case–control studies, the causal relationship formulated by exposure, outcome, and covariates should be firstly understood through a directed acyclic graph, and then reasonable original ORs could be extracted and combined by suitable methods.

Prioritization of interdependent uncertainties in projects

PurposeThe purpose of this paper is to address the limitations of conventional risk matrix based tools such that both positive and negative connotation of uncertainty could be captured within a unified framework that is capable of modeling the direction and strength of causal relationships across uncertainties and prioritizing project uncertainties as both threats and opportunities.Design/methodology/approachTheoretically grounded in the frameworks of Bayesian belief networks (BBNs) and interpretive structural modeling (ISM), this paper develops a structured process for assessing uncertainties in projects. The proposed process is demonstrated by a real application in the construction industry.FindingsProject uncertainties must be prioritized on the basis of their network-wide propagation impact within a network setting of interacting threats and opportunities. Prioritization schemes neglecting interdependencies across project uncertainties might result in selecting sub-optimal strategies. Selection of strategies should focus on both identifying common cause uncertainty triggers and establishing the strength of interdependency between interconnected uncertainties.Originality/valueThis paper introduces a novel approach that integrates both facets of project uncertainties within a project uncertainty network so that decision makers can prioritize uncertainty factors considering the trade-off between threats and opportunities as well as their interactions. The ISM based development of the network structure helps in identifying common cause uncertainty triggers whereas the modeling of a BBN makes it possible to visualize the propagation impact of uncertainties within a network setting. Further, the proposed approach utilizes risk matrix data for project managers to be able to adopt this approach in practice. The proposed process can be used by practitioners while developing uncertainty management strategies, preparing risk management plans and formulating their contract strategy.

Innovative approach to higher education management as an important factor of sustainable economic development

The article shows that innovative approaches to the organization of management of higher education institutions are an important factor in the sustainable development of the economy. In particular, this paper proposes a model for optimizing managerial decisions based on the conducted causal analysis of socio-economic systems. Structural equation modeling (SEM) is widely used to verify conceptual models that determine the direction and strength of causal relationships. The paper proposes to combine the SEM results with the analysis carried out by methods of fuzzy cognitive modeling. This synthesis of models supports what-if analysis and makes it possible to determine the optimal control strategy. The implementation of the proposed model was carried out on data set from the survey of students of the Tashkent State University of Economics studying remotely through a digital platform at the Ural State University of Economics. The purpose of the survey was to analyze student loyalty. The calculations were performed taking into account various input configurations corresponding to specific control strategies

Brent crude oil spot and futures prices: structural break insights

The relationship between oil spot and futures prices has long been a focus of attention, but there is a lack of understanding about how these prices interact in times of crisis. Using cointegration and causality analysis, Brent crude spot and futures prices are examined before, during and after two different types of crises: (1) a supply-led event (the 1990–91 Gulf War) and (2) a demand-led event (the global financial crisis). Structural break analysis was employed to identify the subsamples to be studied. The core findings show evidence of a long-run bidirectional relationship between spot and futures prices. This study provides evidence that different types of crises engender different strengths of causal relationships between Brent crude spot and futures prices.

Relationships between aquatic vegetation and water turbidity: A field survey across seasons and spatial scales.

Field surveys often show that high water turbidity limits cover of aquatic vegetation, while many small-scale experiments show that vegetation can reduce turbidity by decreasing water flow, stabilizing sediments, and competing with phytoplankton for nutrients. Here we bridged these two views by exploring the direction and strength of causal relationships between aquatic vegetation and turbidity across seasons (spring and late summer) and spatial scales (local and regional), using causal modeling based on data from a field survey along the central Swedish Baltic Sea coast. The two best-fitting regional-scale models both suggested that in spring, high cover of vegetation reduces water turbidity. In summer, the relationships differed between the two models; in the first model high vegetation cover reduced turbidity; while in the second model reduction of summer turbidity by high vegetation cover in spring had a positive effect on summer vegetation which suggests a positive feedback of vegetation on itself. Nitrogen load had a positive effect on turbidity in both seasons, which was comparable in strength to the effect of vegetation on turbidity. To assess whether the effect of vegetation was primarily caused by sediment stabilization or a reduction of phytoplankton, we also tested models where turbidity was replaced by phytoplankton fluorescence or sediment-driven turbidity. The best-fitting regional-scale models suggested that high sediment-driven turbidity in spring reduces vegetation cover in summer, which in turn has a negative effect on sediment-driven turbidity in summer, indicating a potential positive feedback of sediment-driven turbidity on itself. Using data at the local scale, few relationships were significant, likely due to the influence of unmeasured variables and/or spatial heterogeneity. In summary, causal modeling based on data from a large-scale field survey suggested that aquatic vegetation can reduce turbidity at regional scales, and that high vegetation cover vs. high sediment-driven turbidity may represent two self-enhancing, alternative states of shallow bay ecosystems.

How multiple causes combine: independence constraints on causal inference.

According to the causal power view, two core constraints—that causes occur independently (i.e., no confounding) and influence their effects independently—serve as boundary conditions for causal induction. This study investigated how violations of these constraints modulate uncertainty about the existence and strength of a causal relationship. Participants were presented with pairs of candidate causes that were either confounded or not, and that either interacted or exerted their influences independently. Consistent with the causal power view, uncertainty about the existence and strength of causal relationships was greater when causes were confounded or interacted than when unconfounded and acting independently. An elemental Bayesian causal model captured differences in uncertainty due to confounding but not those due to an interaction. Implications of distinct sources of uncertainty for the selection of contingency information and causal generalization are discussed.

Environmental health: Assessing risks to society

Natural and built environment systems that sustains lives by providing healthy living surroundings is under a tremendous pressure from various stressors such as rapid population growth, urbanisation, commercialisation of agriculture, industrialisation, psychosocial factors and the like. Environmental health is now a global issue wherein humans act both as the destroyers and the victims. All types of environmental pollutions (air, water, soil, for example) have deleterious effects on human health in manifold magnitudes across the globe. Therefore, it is essential to have a clear understanding of the nature and extent to which a country is running a risk of environmental health hazards to its society. Considering this in mind, the present paper introduces a new way of looking and assessing the health effects of environmental hazards and pollutions. This new measure, based on a holistic view and system modelling approach, conceptualises, measures and facilitates the management of the multifarious phenomenon of environmental health. It develops, constructs and validates a robust model of management with measurement and thus provides a management strategy to control and improve environmental health. This Kanji-Chopra environmental health model has been especially devised and developed to assess and manage environmental health risks to society by using and constructing a latent variable structural equations model within the certain boundaries of the country's natural and built environment system. It provides a measurement or index of environmental health indicating the extent to which a particular society is experiencing environmental health hazards. Path coefficients indicate the strength of causal relationships among different dimensions of environmental health. The scores of manifest variables of different dimensions of the model pinpoint what exactly is required from the authorities and individuals to improve environmental health in order to mitigate its risks to society.

Using Bayesian Networks to complement conventional analyses to explore landholder management of native vegetation

Influencing the management of private landholders is a key element of improving the condition of Australia’s natural resources. Despite substantial investment by governments, effecting behavioural change on a scale likely to stem biodiversity losses has proven difficult. Understanding landholder decision-making is now acknowledged as fundamental to achieving better policy outcomes. There is a large body of research examining landholder adoption of conservation practices. Social researchers are able to employ a suite of conventional techniques to analyse their survey data and assist in identifying significant and causal relationships between variables. However, these techniques can be limited by the type of data available, the breadth of issues that can be represented and the extent that causality can be explored. In this paper we discuss the findings of a unique study exploring the benefits of combining Bayesian Networks (BNs) with conventional statistical analysis to examine landholder adoption. Our research examined the landholder fencing of native bushland in the Wimmera region in south east Australia. Findings from this study suggest that BNs provided enhanced understanding of the presence and strength of causal relationships. There was also the additional benefit that a BN could be quickly developed and that this process helped the research team clarify and understand relationships between variables. However, a key finding was that the interpretation of the results of the BNs was complemented by the conventional data analysis and expert review. An additional benefit of the BNs is their capacity to present key findings in a format that is more easily interpreted by researchers and enables researchers to more easily communicate their findings to natural resource practitioners and policy makers.

Contiguity and covariation in human causal inference

Nearly every theory of causal induction assumes that the existence and strength of causal relations needs to be inferred from observational data in the form of covariations. The last few decades have seen much controversy over exactly how covariations license causal conjectures. One consequence of this debate is that causal induction research has taken for granted that covariation information is readily available to reasoners. This perspective is reflected in typical experimental designs, which either employ covariation information in summary format or present participants with clearly marked discrete learning trials. I argue that such experimental designs oversimplify the problem of causal induction. Real-world contexts rarely are structured so neatly; rather, the decision about whether a cause and effect co-occurred on a given occasion constitutes a key element of the inductive process. This article will review how the event-parsing aspect of causal induction has been and could be addressed in associative learning and causal power theories.

Detection of causal relationships between factors influencing adverse side-effects from anaesthesia and convalescence following surgery: a path analytical approach.

The anaesthesiologist's preoperative interview with the patient is important in preparing the patient for surgery. Its potential protective influence on adverse side-effects from anaesthesia and convalescence is rarely investigated within the context of other perioperative factors. Structural equation modelling allows detection and quantification of all causal relationships and mediator effects in multivariate models. Therefore, this method is presented as a tool and applied to discover the influence of the preoperative interview within socio-demographic variables and duration of surgery on complaints and recovery after anaesthesia. The influence of individual satisfaction with the anaesthesiologist's preoperative interview on postoperative events such as nausea/vomiting, difficulties in recovering from anaesthesia, experience of postoperative pain, physical discomfort and satisfaction with convalescence expressed by the patient was analysed by means of structural equation modelling. The variables gender, age and duration of surgery were also included as predictors in the analyses. The model in the total sample of 710 patients was then analysed for structural differences between groups treated either with propofol (n = 204) or with isoflurane + nitrous oxide (n = 267) for maintenance of anaesthesia. The model revealed that the anaesthesiologist's preoperative interview in combination with associated mediating side-effects explains 45% of the variance of 'feeling physical discomfort' and 18% of the variance of 'satisfaction with convalescence'. The same model could be fitted in the propofol and the isoflurane + nitrous oxide group. Moreover, the structure and the strength of causal relations between variables were identical in the two groups. The anaesthesiologist's efforts to improve the interview with the patient by more reassuring and proper information will result in less side-effects from anaesthesia and better recovery from surgery. It could be demonstrated that structural equation modelling is a powerful tool for detection of causal relationships and mediator effects in perioperative medicine.

Detection of causal relationships between factors influencing adverse side-effects from anaesthesia and convalescence following surgery: a path analytical approach

Background and objective: The anaesthesiologist's preoperative interview with the patient is important in preparing the patient for surgery. Its potential protective influence on adverse side-effects from anaesthesia and convalescence is rarely investigated within the context of other perioperative factors. Structural equation modelling allows detection and quantification of all causal relationships and mediator effects in multivariate models. Therefore, this method is presented as a tool and applied to discover the influence of the preoperative interview within socio-demographic variables and duration of surgery on complaints and recovery after anaesthesia. Methods: The influence of individual satisfaction with the anaesthesiologist's preoperative interview on postoperative events such as nausea/vomiting, difficulties in recovering from anaesthesia, experience of postoperative pain, physical discomfort and satisfaction with convalescence expressed by the patient was analysed by means of structural equation modelling. The variables gender, age and duration of surgery were also included as predictors in the analyses. The model in the total sample of 710 patients was then analysed for structural differences between groups treated either with propofol (n = 204) or with isoflurane + nitrous oxide (n = 267) for maintenance of anaesthesia. Results: The model revealed that the anaesthesiologist's preoperative interview in combination with associated mediating side-effects explains 45% of the variance of 'feeling physical discomfort' and 18% of the variance of 'satisfaction with convalescence'. The same model could be fitted in the propofol and the isoflurane + nitrous oxide group. Moreover, the structure and the strength of causal relations between variables were identical in the two groups. Conclusions: The anaesthesiologist's efforts to improve the interview with the patient by more reassuring and proper information will result in less side-effects from anaesthesia and better recovery from surgery. It could be demonstrated that structural equation modelling is a powerful tool for detection of causal relationships and mediator effects in perioperative medicine.

Weighing the evidence of ecological risk from chemical contamination in the estuarine environment adjacent to the Portsmouth Naval Shipyard, Kittery, Maine, USA

In characterizing ecological risks, considerable consensus building and professional judgments are required to develop conclusions about risk. This is because how to evaluate all the factors that determine ecological risk is not well defined and is subject to interpretation. Here we report on the application of a procedure to weigh the evidence of ecological risk and develop conclusions about risk that will incorporate the strengths and weaknesses of the assessment. The procedure was applied to characterize ecological risk of chemical contamination in nearshore areas adjacent to the Portsmouth Naval Shipyard, located at the mouth of the Great Bay Estuary, New Hampshire and Maine, USA. Measures of exposure and effect were used to interpret the magnitude of risk to the assessment endpoints of pelagic species, epibenthic species, the benthic community, eelgrass plants, the salt marsh community, and avian receptors. The evidence of chemical exposure from water, sediment, and tissue and the evidence of biological effects to representative pelagic, epibenthic, benthic, eelgrass, salt marsh, and avian species were weighed to characterize ecological risk. Individual measures were weighted by the quality and reliability of their data and risk was estimated from the preponderance, magnitude, extent, and strength of causal relationships between the data on exposure and effects. Relating evidence of risk to hypothesized pathways of exposure made it possible to estimate the magnitude of risk from sediment and water and express the confidence associated with the findings. Systematically weighing the evidence of risk rendered conclusions about risk in a manner that was clearly defined, objective, consistent, and did not rely solely on professional judgment.

Similarities and Differences in the Implicit Causal Models of Faculty and Students

Do faculty members and students share the same underlying cognitive models? A specially-developed causal matrix was completed by 15 faculty members of the Department of Behavioral Sciences and 32 students enrolled in Introductory Psychology. Analyses of results suggest marked differences in the implicit models of these two groups. Compared to faculty, students do not differentiate causes from effects, generally overrate the number and strength of causal relationships, and include recursive relationships in their modal model. Several pedagogical implications of these findings are discussed.