Estimating and testing mediation and moderation in within-subject designs.

Analyses designed to detect mediation and moderation of treatment effects are increasingly prevalent in research in psychology. The mediation question concerns the processes that produce a treatment effect. The moderation question concerns factors that affect the magnitude of that effect. Although analytic procedures have been reasonably well worked out in the case in which the treatment varies between participants, no systematic procedures for examining mediation and moderation have been developed in the case in which the treatment varies within participants. The authors present an analytic approach to these issues using ordinary least squares estimation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Methods for integrating moderation and mediation: A general analytical framework using moderated path analysis.

Studies that combine moderation and mediation are prevalent in basic and applied psychology research. Typically, these studies are framed in terms of moderated mediation or mediated moderation, both of which involve similar analytical approaches. Unfortunately, these approaches have important shortcomings that conceal the nature of the moderated and the mediated effects under investigation. This article presents a general analytical framework for combining moderation and mediation that integrates moderated regression analysis and path analysis. This framework clarifies how moderator variables influence the paths that constitute the direct, indirect, and total effects of mediated models. The authors empirically illustrate this framework and give step-by-step instructions for estimation and interpretation. They summarize the advantages of their framework over current approaches, explain how it subsumes moderated mediation and mediated moderation, and describe how it can accommodate additional moderator and mediator variables, curvilinear relationships, and structural equation models with latent variables. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Socioeconomic position, health behaviors, and C-reactive protein: A moderated-mediation analysis.

Objective: We sought to understand the link between low socioeconomic position (SEP) and cardiovascular disease (CVD) by examining the association between SEP, health-related coping behaviors, and C-reactive protein (CRP), an inflammatory marker and independent risk factor for CVD, in a U.S. sample of adults. Design: We used a multiple mediation model to evaluate how these behaviors work in concert to influence CRP levels and whether these relationships were moderated by gender and race/ethnicity. Main outcome measures: CRP levels were divided into two categories: elevated CRP (3.1–10.0 mg/L) and normal CRP (≤3.0 mg/L). Results: Both poverty and low educational attainment were associated with elevated CRP, and these associations were primarily explained through higher levels of smoking and lower levels of exercise. In the education model, poor diet also emerged as a significant mediator. These behaviors accounted for 87.9% of the total effect of education on CRP and 55.8% the total effect of poverty on CRP. We also found significant moderation of these mediated effects by gender and race/ethnicity. Conclusion: These findings demonstrate the influence of socioeconomically patterned environmental constraints on individual-level health behaviors. Specifically, reducing socioeconomic inequalities may have positive effects on CVD disparities through reducing cigarette smoking and increasing vigorous exercise. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A moderated mediation model of the relationship between organizational citizenship behaviors and job performance.

Addressing numerous calls for future research on understanding the theoretical mechanisms that explain the relationship between organizational citizenship behaviors (OCBs) and job performance, this study focused on how an employee's relationships with coworkers mediate the relationship between his or her OCBs and his or her job performance. It also looked at how task autonomy might moderate this mediated relationship. The results of an empirical study involving 364 jewelry designers, 310 coworkers, and 284 supervisors indicated that coworker relations mediated the relationship between OCBs and job performance. In addition, task autonomy positively moderated both paths of this mediated relationship. Finally, these results hold for OCBs that are targeted at individuals but not for OCBs that are targeted toward organizations. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

The moderating role of safety-specific trust on the relation between safety-specific leadership and safety citizenship behaviors.

The authors examined whether safety-specific trust moderates or mediates the relationship between safety-specific transformational leadership and subordinates' safety citizenship behavior. Data from 139 subordinate-supervisor dyads were collected from the United Kingdom construction industry and analyzed using hierarchical regression models. Results showed that safety-specific trust moderated rather than mediated the effects of safety-specific transformational leaders on subordinates' behavior. Specifically, in conditions of high and moderate safety-specific trust, leaders had a significant effect on subordinates' safety citizenship behavior. However, in conditions of low safety-specific trust, leaders did not significantly influence subordinates' safety citizenship behavior. The implications of these findings for general safety theory and practice are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Cognitive impairment influences drinking outcome by altering therapeutic mechanisms of change.

Serious neuropsychological impairments are seen in a minority of addiction treatment clients, and, theoretically, these impairments should undermine behavioral changes targeted by treatment; however, little evidence supports a direct influence of impairment on treatment response. To address this paradox, the authors used structural equation modeling and Project MATCH data (N=1,726) to examine direct, mediated, and moderated paths between cognitive impairment, therapeutic processes, and treatment outcome. Mediated relations were found, wherein impairment led to less treatment compliance, lower self-efficacy, and greater Alcoholics Anonymous Involvement, which, in turn, more proximally predicted drinking. Impairment further moderated the effect of self-efficacy, making it a poor predictor of drinking outcomes in impaired clients, thereby suggesting that impaired and unimpaired clients traverse different pathways to addiction recovery. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The influence of psychological flexibility on work redesign: Mediated moderation of a work reorganization intervention.

This quasi-experiment tested the extent to which an individual characteristic, psychological flexibility, moderated the effects of a control-enhancing work reorganization intervention in a call center. Results indicated that, compared with a control group, this intervention produced improvements in mental health and absence rates, particularly for individuals with higher levels of psychological flexibility. Findings also showed that these moderated intervention effects were mediated by job control. Specifically, the intervention enhanced perceptions of job control, and hence its outcomes, for the people who received it, especially for those who had greater psychological flexibility. Discussion highlights the benefits of understanding the processes (e.g., mediators, moderators, and mediated moderators) involved in work reorganization interventions. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Preliminary evidence for cognitive mediation during cognitive-behavioral therapy of panic disorder.

Cognitive-behavioral therapy (CBT) and pharmacotherapy are similarly effective for treating panic disorder with mild or no agoraphobia, but little is known about the mechanism through which these treatments work. The present study examined some of the criteria for cognitive mediation of treatment change in CBT alone, imipramine alone, CBT plus imipramine, and CBT plus placebo. Ninety-one individuals who received 1 of these interventions were assessed before and after acute treatment, and after a 6-month maintenance period. Multilevel moderated mediation analyses provided preliminary support for the notion that changes in panic-related cognitions mediate changes in panic severity only in treatments that include CBT. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Review of Moderation as a goal or outcome of treatment for alcohol problems: A dialogue.

Reviews the book, Moderation as a goal or outcome of treatment for alcohol problems: A dialogue edited by Mark B. Sobell and Linda C. Sobell (1987). The papers were originally published as a separate volume of Drugs and Society in 1986. In addition to the six original papers that deal with moderate drinking as both a treatment goal and a treatment outcome, the volume includes a Preface, a Foreword, and a concluding chapter that provide needed perspective on these important, if not contentious, issues. This is a lively and interesting collection of essays, which will amuse the curious, confuse the dogmatists, and confound the critics. Consider advocates of moderation goals admitting the validity of the disease concept, representatives of the total abstinence camp suggesting why moderation outcomes may indeed be valid, cognitive behavioral therapists arguing cogently for abstinence-oriented treatment (which they do more often than moderation treatments anyway), clinical psychologists arguing that their profession must accept abstinence as a treatment goal before they can expect to have an impact on the health care delivery system, and behavioral theorists openly espousing cognitive mediators and motivational constructs while arguing that their approach relies only on "observable" data. These and even more ideological incongruities are in store for the patient and attentive reader. The most disappointing impression that emerges from a cumulative reading of this volume is that behavioral psychology has not lived up to its promises and promise. Although these chapters make an excellent case for the potential contributions of behavior theory to both traditional and innovative treatment approaches, they suffer from the lack of a coherent concept of alcoholism to rival the dominant disease concept. Nowhere in these papers is there a credible theory of alcoholism, nor are there any clear attempts to interpret the dependence syndrome concept, which has become a dominant organizing principle in diagnosis and treatment in terms of its origins in psychological learning theory. Furthermore, little recognition is given to other relevant variables that need to be taken into account in treating problem drinkers with moderation goals, such as possible genetic vulnerabilities and the importance of psychiatric disorder. To end on a positive note, the reader will find that the goal of moderation is apparent in this volume in more ways than its title would imply. Gone is the stridency and contentiousness that have invited the intemperate critics of behaviorism to ignore its message. It is unfortunate that a real dialogue could not have been conducted with more of the advocates of abstinence-oriented treatment invited to present their arguments. Judging from the contents of this book, the commonalities would have been sufficient to begin a vitally needed rapprochement between the social, behavioral, biological, and political constituencies in this field. Nevertheless, Mark and Linda Sobell are to be complemented for initiating the dialogue. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Respiratory and cognitive mediators of treatment change in panic disorder: Evidence for intervention specificity.

Objective: There are numerous theories of panic disorder, each proposing a unique pathway of change leading to treatment success. However, little is known about whether improvements in proposed mediators are indeed associated with treatment outcomes and whether these mediators are specific to particular treatment modalities. Our purpose in this study was to analyze pathways of change in theoretically distinct interventions using longitudinal, moderated mediation analyses. Method: Forty-one patients with panic disorder and agoraphobia were randomly assigned to receive 4 weeks of training aimed at altering either respiration (capnometry-assisted respiratory training) or panic-related cognitions (cognitive training). Changes in respiration (PCO?, respiration rate), symptom appraisal, and a modality-nonspecific mediator (perceived control) were considered as possible mediators. Results: The reductions in panic symptom severity and panic-related cognitions and the improvements in perceived control were significant and comparable in both treatment groups. Capnometry-assisted respiratory training, but not cognitive training, led to corrections from initially hypocapnic to normocapnic levels. Moderated mediation and temporal analyses suggested that in capnometry-assisted respiratory training, PCO? unidirectionally mediated and preceded changes in symptom appraisal and perceived control and was unidirectionally associated with changes in panic symptom severity. In cognitive training, reductions in symptom appraisal were bidirectionally associated with perceived control and panic symptom severity. In addition, perceived control was bidirectionally related to panic symptom severity in both treatment conditions. Conclusion: The findings suggest that reductions in panic symptom severity can be achieved through different pathways, consistent with the underlying models. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A critical reappraisal of divorce mediation research and policy.

Because of the many problems associated with litigating divorce disputes, mediation has been proposed as an alternative. Its proponents, claiming wide-ranging benefits for both the litigants and the legal system, have had tremendous success in advancing mediation in social policy. This article critically assesses the validity of these claimed benefits. The article first considers the role of pro se representation and its potential consequences for evaluating divorce mediation because of the increased use of pro se representation in these cases. The article then articulates the goals attributed to the mediation procedure and its clients, identifies the behavioral assumptions underlying those goals, and critically reviews the social science research and theory that have directly tested the validity of the goals and assumptions or are indirectly relevant to the analysis (B. D. Sales, 1983). It is concluded that the goals of divorce mediation may have been and may be overly optimistic. The implications of these findings for mediation practice and policy are considered. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Yes, but what’s the mechanism? (don’t expect an easy answer).

Psychologists increasingly recommend experimental analysis of mediation. This is a step in the right direction because mediation analyses based on nonexperimental data are likely to be biased and because experiments, in principle, provide a sound basis for causal inference. But even experiments cannot overcome certain threats to inference that arise chiefly or exclusively in the context of mediation analysis—threats that have received little attention in psychology. The authors describe 3 of these threats and suggest ways to improve the exposition and design of mediation tests. Their conclusion is that inference about mediators is far more difficult than previous research suggests and is best tackled by an experimental research program that is specifically designed to address the challenges of mediation analysis. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Criminal thinking as a mediator of the mental illness–prison violence relationship: A path analytic study and causal mediation analysis.

Although mental illness and violence correlate, it has been speculated that this relationship is mediated by a series of third variables. The current study examined the possibility that the relationship between mental illness and prison violence is mediated by criminal thinking. General criminal thinking, as measured by the General Criminal Thinking (GCT) score of the Psychological Inventory of Criminal Thinking Styles (PICTS; Walters, 1995), was tested as a possible mediator of the mental illness–prison violence relationship. Using a prospective design and path analytic statistical technique, it was determined that general criminal thinking served as a partial mediator of the mental illness-institutional violence nexus in a sample of 2,487 male prison inmates. Causal mediation analysis also documented the presence of a small but statistically significant mediating role for general criminal thinking in this study. The implications of these results for understanding, predicting, and managing violent behavior in severely mentally ill inmates are discussed. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Bias in cross-sectional analyses of longitudinal mediation.

Most empirical tests of mediation utilize cross-sectional data despite the fact that mediation consists of causal processes that unfold over time. The authors considered the possibility that longitudinal mediation might occur under either of two different models of change: (a) an autoregressive model or (b) a random effects model. For both models, the authors demonstrated that cross-sectional approaches to mediation typically generate substantially biased estimates of longitudinal parameters even under the ideal conditions when mediation is complete. In longitudinal models where variable M completely mediates the effect of X on Y, cross-sectional estimates of the direct effect of X on Y, the indirect effect of X on Y through M, and the proportion of the total effect mediated by M are often highly misleading. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Effect size measures for mediation models: Quantitative strategies for communicating indirect effects.

The statistical analysis of mediation effects has become an indispensable tool for helping scientists investigate processes thought to be causal. Yet, in spite of many recent advances in the estimation and testing of mediation effects, little attention has been given to methods for communicating effect size and the practical importance of those effect sizes. Our goals in this article are to (a) outline some general desiderata for effect size measures, (b) describe current methods of expressing effect size and practical importance for mediation, (c) use the desiderata to evaluate these methods, and (d) develop new methods to communicate effect size in the context of mediation analysis. The first new effect size index we describe is a residual-based index that quantifies the amount of variance explained in both the mediator and the outcome. The second new effect size index quantifies the indirect effect as the proportion of the maximum possible indirect effect that could have been obtained, given the scales of the variables involved. We supplement our discussion by offering easy-to-use R tools for the numerical and visual communication of effect size for mediation effects. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

The Attenuating Effect of Role Overload on Relationships Linking Self-Efficacy and Goal Level to Work Performance.

The reported research examines the moderating effects of role overload on the antecedents and consequences of self-efficacy and personal goal level in a longitudinal study conducted in an industrial selling context. The results indicate that role overload moderates the antecedent effect of perceived organizational resources on self-efficacy beliefs. They also show that role overload moderates the direct effects of both self-efficacy and goal level on performance, such that these relationships are positive when role overload is low but not significant when role overload is high. Further, the results reveal a pattern of moderated mediation, in which goal level mediates the indirect effect of self-efficacy on performance when role overload is low but not when it is high. Implications for theory and managerial practice are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Establishing the next generation at work: Leader generativity as a moderator of the relationships between leader age, leader-member exchange, and leadership success.

In this study, the authors investigated leader generativity as a moderator of the relationships between leader age, leader-member exchange, and three criteria of leadership success (follower perceptions of leader effectiveness, follower satisfaction with leader, and follower extra effort). Data came from 128 university professors paired with one research assistant each. Results showed positive relationships between leader age and leader generativity, and negative relationships between leader age and follower perceptions of leader effectiveness and follower extra effort. Consistent with expectations based on leadership categorization theory, leader generativity moderated the relationships between leader age and all three criteria of leadership success, such that leaders high in generativity were better able to maintain high levels of leadership success at higher ages than leaders low in generativity. Finally, results of mediated moderation analyses showed that leader-member exchange quality mediated these moderating effects. The findings suggest that, in combination, leader age and the age-related construct of generativity importantly influence leadership processes and outcomes. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Mediators, moderators, and tests for mediation.

Discusses mediation relations in causal terms. Influences of an antecedent are transmitted to a consequence through an intervening mediator. Mediation relations may assume a number of functional forms, including nonadditive, nonlinear, and nonrecursive forms. Although mediation and moderation are distinguishable processes, with nonadditive forms (moderated mediation) a particular variable may be both a mediator and a moderator within a single set of functional relations. Current models for testing mediation relations in industrial and organizational psychology often involve an interplay between exploratory (correlational) statistical tests and causal inference. It is suggested that no middle ground exists between exploratory and confirmatory (causal) analysis and that attempts to explain how mediation processes occur require specified causal models. (57 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Moderators and mediators of exercise-induced objective sleep improvements in midlife and older adults with sleep complaints.

Objective: Exercise can improve sleep quality, but for whom and by what means remains unclear. We examined moderators and mediators of objective sleep improvements in a 12-month randomized controlled trial among underactive midlife and older adults reporting mild/moderate sleep complaints. Methods: Participants (N = 66, 67% women, 55–79 years) were randomized to moderate-intensity exercise or health education control. Putative moderators were gender, age, physical function, self-reported global sleep quality, and physical activity levels. Putative mediators were changes in BMI, depressive symptoms, and physical function at 6 months. Objective sleep outcomes measured by in-home polysomnography were percent time in Stage I sleep, percent time in Stage II sleep, and number of awakenings during the first third of sleep at 12 months. Results: Baseline physical function and sleep quality moderated changes in Stage I sleep; individuals with higher initial physical function (p = .01) and poorer sleep quality (p = .03) had greater improvements. Baseline physical activity level moderated changes in Stage II sleep (p = .04) and number of awakenings (p = .01); more sedentary individuals had greater improvements. Decreased depressive symptoms (CI:-1.57 to ?0.02) mediated change in Stage I sleep. Decreased depressive symptoms (CI:-0.75 to ?0.01), decreased BMI (CI:-1.08 to ?0.06), and increased physical function (CI: 0.01 to 0.72) mediated change in number of awakenings. Conclusions: Initially less active individuals with higher initial physical function and poorer sleep quality improved the most. Affective, functional, and metabolic mediators specific to sleep architecture parameters were suggested. These results indicate strategies to more efficiently treat poor sleep through exercise in older adults. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Personality and leader effectiveness: A moderated mediation model of leadership self-efficacy, job demands, and job autonomy.

The trait theory of leadership is advanced by a joint investigation of the mediating role of (a) leadership self-efficacy (LSE = leader's perceived capabilities to perform leader roles) in linking neuroticism, extraversion, and conscientiousness with leader effectiveness and (b) the moderating role of job demands and job autonomy in influencing the mediation. Using K. J. Preacher, D. D. Rucker, and A. F. Hayes' (2007) moderated mediation framework, the authors tested the model (over a 2-year period) with matched data from 394 military leaders and their supervisors. Results showed that LSE mediated the relationships for neuroticism, extraversion, and conscientiousness with leader effectiveness. Moderated mediation analyses further revealed that LSE mediated the relationships for (a) all 3 personality variables for only those leaders with low job demands; (b) neuroticism and conscientiousness for only those leaders with high job autonomy; and (c) extraversion, regardless of a leader's level of job autonomy. Results underscore the importance of accounting for leaders' situational contexts when examining the relationships between personality, LSE, and effectiveness. (PsycINFO Database Record (c) 2010 APA, all rights reserved)