Lower level mediation in multilevel models

Multilevel models are increasingly used to estimate models for hierarchical and repeated measures data. The authors discuss a model in which there is mediation at the lower level and the mediational links vary randomly across upper level units. One repeated measures example is a case in which a person's daily stressors affect his or her coping efforts, which affect his or her mood, and both links vary randomly across persons. Where there is mediation at the lower level and the mediational links vary randomly across upper level units, the formulas for the indirect effect and its standard error must be modified to include the covariance between the random effects. Because no standard method can estimate such a model, the authors developed an ad hoc method that is illustrated with real and simulated data. Limitations of this method and characteristics of an ideal method are discussed.     

Corporate social responsibility and work engagement: testing a moderated mediation model

The purpose of this study is to examine the mediating role of collective self-esteem in the relationship between employees’ perceived corporate social responsibility (CSR) and their work engagement. We also explore the moderating role of employees’ concern for face in the linkage between their perceived CSR and collective self-esteem. A two-wave panel data from a final sample of 217 employees in six companies in Wuhan, China, completed the questionnaire survey. Employees’ perceived CSR has a direct and positive effect on their work engagement, which is partially mediated by their collective self-esteem. Furthermore, employees’ concern for face moderates the relationship between their perceived CSR and collective self-esteem. CSR has a stronger effect on collective self-esteem for employees who concern more for face than for those who concern less for face. Understanding the outcomes, the mediating mechanisms, as well as the boundary conditions of perceived CSR on work engagement, help firms to better formulate their CSR strategy. First, we introduce collective self-esteem as an important mediating mechanism in the relationship between CSR and employees’ work engagement. Second, we identify concern for face as an important limiting condition in the linkage between CSR and employees’ collective self-esteem. Finally, previous research investigating employees’ reactions to CSR has predominantly been conducted in the West. We conduct our study in the Chinese or Confucian context to provide some new and complementary insights.     

Assessing moderated mediation in linear models requires fewer confounding assumptions than assessing mediation

It is well known from the mediation analysis literature that the identification of direct and indirect effects relies on strong no unmeasured confounding assumptions of no unmeasured confounding. Even in randomized studies the mediator may still be correlated with unobserved prognostic variables that affect the outcome, in which case the mediator's role in the causal process may not be inferred without bias. In the behavioural and social science literature very little attention has been given so far to the causal assumptions required for moderated mediation analysis. In this paper we focus on the index for moderated mediation, which measures by how much the mediated effect is larger or smaller for varying levels of the moderator. We show that in linear models this index can be estimated without bias in the presence of unmeasured common causes of the moderator, mediator and outcome under certain conditions. Importantly, one can thus use the test for moderated mediation to support evidence for mediation under less stringent confounding conditions. We illustrate our findings with data from a randomized experiment assessing the impact of being primed with social deception upon observer responses to others’ pain, and from an observational study of individuals who ended a romantic relationship assessing the effect of attachment anxiety during the relationship on mental distress 2 years after the break‐up.     

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.     

Testing mediation effects in cross-classified multilevel data

In this article, we propose an approach to test mediation effects in cross-classified multilevel data in which the initial cause is associated with one crossed factor, the mediator is associated with the other crossed factor, and the outcome is associated with Level-1 units (i.e., the 2^(A)?2^(B)?1 design). Multiple-membership models and cross-classified random effects models are used to estimate the indirect effects. The method is illustrated using real data from the Early Childhood Longitudinal Study–Kindergarten Cohort (1998). The results from the simulation study show that the proposed method can produce a consistent estimate of the indirect effect and reliable statistical inferences, given an adequate sample size.     

Mediation in experimental and nonexperimental studies: new procedures and recommendations

Mediation is said to occur when a causal effect of some variable X on an outcome Y is explained by some intervening variable M. The authors recommend that with small to moderate samples, bootstrap methods (B. Efron & R. Tibshirani, 1993) be used to assess mediation. Bootstrap tests are powerful because they detect that the sampling distribution of the mediated effect is skewed away from 0. They argue that R. M. Baron and D. A. Kenny's (1986) recommendation of first testing the X --> Y association for statistical significance should not be a requirement when there is a priori belief that the effect size is small or suppression is a possibility. Empirical examples and computer setups for bootstrap analyses are provided.     

Supervisors' upward exchange relationships and subordinate outcomes: testing the multilevel mediation role of empowerment

This study empirically examined the proposition that supervisors' exchange relationships with their own supervisors (i.e., leader-leader exchange, or LLX) are related to their subordinates' work-related outcomes through 3 mechanisms: (a) leaders modeling their LLX to develop and maintain their exchange relationships with their subordinates (i.e., leader-member exchange, or LMX), (b) motivating the team and its members, captured by team and individual empowerment, and (c) facilitating the relationships between LMX and individual outcomes. Analyses of multisource and lagged data from 104 team supervisors and 577 subordinates showed that LMX mediated the positive relationship of LLX on subordinates' individual empowerment. Furthermore, team empowerment and individual empowerment sequentially mediated the positive relationships between LLX and subordinates' job satisfaction and job performance. The authors also found that the indirect relationships of LMX with job satisfaction and job performance via individual empowerment were stronger when LLX was higher. Theoretical and practical implications of these findings are discussed.     

Dental flossing and automaticity: a longitudinal moderated mediation analysis

We investigated the role of normative support, behavioural automaticity, and action control in predicting dental flossing behaviour. Between May and October 2015, 629 Australian young adults completed a questionnaire assessing constructs of normative support and automaticity, and a 2-week follow-up of dental flossing behaviour and action control, resulting in n = 241 persons for longitudinal analysis. Findings supported the hypotheses that the effect of normative support on behaviour would be mediated via automaticity, and the effect of automaticity would be moderated by action control. Current results extend previous research to elucidate the mechanisms that help to understand predictors of oral hygiene behaviours and contribute to the cumulative evidence concerning self-regulatory and automatic components of health behaviour.     

社会自我效能感与工作倦怠的关系：社会交换视角下有调节的中介模型

本研究基于工作要求-资源模型和领导-成员交换理论,采用两时点追踪问卷调查方法收集了313份数据,探讨了员工的社会自我效能感与工作倦怠之间的关系及其内在机制。分析结果表明：社会自我效能感对工作倦怠有显著的负向预测作用;领导-成员交换关系在社会自我效能感和工作倦怠之间有着显著的中介作用;领导-成员交换社会比较调节了社会自我效能感通过领导-成员交换关系预测工作倦怠的间接效应。     

Depression, impulsivity and health-related disability: A moderated mediation analysis

The goal of the current study is to examine how impulsivity affects the relationship between depression and health-related disability. Specifically, we examined impulsivity as a possible moderator of this relationship, as well as alcohol use, smoking, and binge eating as possible mediators. The study utilized the Collaborative Psychiatric Epidemiological Surveys (N = 20,013, mean age = 43.38, female = 57.3%). We conducted a series of moderated mediation analyses to test hypotheses. In all analyses, the relationship between depression and health-related disability was mediated by each maladaptive coping behavior, and the relationship between depression and the behavior was moderated by impulsivity. The study supports the utility of examining the individual difference mechanisms that might drive the relationship between depression and health-related disability.     

Supervisor undermining and driving errors in truck drivers: A moderated mediation model

The present study focuses on the detrimental impact of supervisor undermining behaviors at work on driving errors for truck drivers, arguing for the mediating role of burnout. Moreover, this research highlights the moderating role of general self-efficacy in the relationships between supervisor undermining and burnout, and between burnout and driving errors, respectively. The data collected from a sample of 190 Romanian drivers supported a moderated mediation model in which burnout partially mediates the relation between supervisor undermining and driving errors, while self-efficacy moderates both aforementioned relationships. The conditional indirect effect of supervisor undermining on driving errors was significant when self-efficacy was low and non-significant when self-efficacy was high. Overall, our results emphasize the negative impact that supervisor undermining and burnout have on driving errors, while also highlighting the buffering effect of self-efficacy.     

工作压力对建设型和防御型建言的差异影响

以往研究普遍从建言行为的建设性意图特征出发, 探讨其关键前因、产生机制和情境因素, 但却较少关注建言行为的工具性目的。基于资源保存理论, 本研究构建了有调节的中介模型以探讨工作压力影响员工建设型建言和防御型建言的作用机制和边界条件。通过对某建筑企业386名员工进行两阶段调查, 结果表明：工作压力与防御型建言存在正向相关关系, 与建设型建言存在负向相关关系, 自我损耗在其中起中介作用; 另外, 领导开明性正向调节自我损耗和建设型建言的负向相关关系, 并正向调节工作压力通过自我损耗影响建设型建言的间接效应。     

Negative emotions and quality of life among adolescents: A moderated mediation model

Background/ObjectiveDepression, anxiety and stress are known as negative emotions. Previous studies have shown that negative emotions were associated with quality of life. There are a lot of researches on quality of life. However, previous studies mainly focused on health-related quality of life among patients. This study aims to examine the relationship between negative emotions and quality of life as well as the underlying psychological mechanism among community-based samples.MethodWe surveyed 6,401 adolescents (age: 9-15 years old). Participants were assessed using the Depression Anxiety Stress Scale, Resilience Scale for Chinese Adolescent, Perceived Social Support Scale and the Pediatric Quality of Life Inventory 4.0 Generic Scale for Negative Emotions, Resilience, Social Support and Quality of Life.ResultsResults revealed that negative emotions were negatively associated with quality of life, and resilience mediated the relationship between negative emotions and quality of life. Social support moderated all the paths among negative emotions, resilience and quality of life.ConclusionsAdolescents’ quality of life was indirectly affected by negative emotions via resilience, and less affected by negative emotions and more affected by resilience with the improvement of social support. The theoretical and practical implications of these results are discussed.     

Analysing multisource feedback with multilevel structural equation models: Pitfalls and recommendations from a simulation study

When multisource feedback instruments, for example, 360-degree feedback tools, are validated, multilevel structural equation models are the method of choice to quantify the amount of reliability as well as convergent and discriminant validity. A non-standard multilevel structural equation model that incorporates self-ratings (level-2 variables) and others’ ratings from different additional perspectives (level-1 variables), for example, peers and subordinates, has recently been presented. In a Monte Carlo simulation study, we determine the minimal required sample sizes for this model. Model parameters are accurately estimated even with the smallest simulated sample size of 100 self-ratings and two ratings of peers and of subordinates. The precise estimation of standard errors necessitates sample sizes of 400 self-ratings or at least four ratings of peers and subordinates. However, if sample sizes are smaller, mainly standard errors concerning common method factors are biased. Interestingly, there are trade-off effects between the sample sizes of self-ratings and others’ ratings in their effect on estimation bias. The degree of convergent and discriminant validity has no effect on the accuracy of model estimates. The χ² test statistic does not follow the expected distribution. Therefore, we suggest using a corrected level-specific standardized root mean square residual to analyse model fit and conclude with further recommendations for applied organizational research.     

The relationship between multilevel models and non‐parametric multilevel mixture models: Discrete approximation of intraclass correlation,random coefficient distributions,and residual heteroscedasticity

Multilevel data structures are common in the social sciences. Often, such nested data are analysed with multilevel models (MLMs) in which heterogeneity between clusters is modelled by continuously distributed random intercepts and/or slopes. Alternatively, the non‐parametric multilevel regression mixture model (NPMM) can accommodate the same nested data structures through discrete latent class variation. The purpose of this article is to delineate analytic relationships between NPMM and MLM parameters that are useful for understanding the indirect interpretation of the NPMM as a non‐parametric approximation of the MLM, with relaxed distributional assumptions. We define how seven standard and non‐standard MLM specifications can be indirectly approximated by particular NPMM specifications. We provide formulas showing how the NPMM can serve as an approximation of the MLM in terms of intraclass correlation, random coefficient means and (co)variances, heteroscedasticity of residuals at level 1, and heteroscedasticity of residuals at level 2. Further, we discuss how these relationships can be useful in practice. The specific relationships are illustrated with simulated graphical demonstrations, and direct and indirect interpretations of NPMM classes are contrasted. We provide an R function to aid in implementing and visualizing an indirect interpretation of NPMM classes. An empirical example is presented and future directions are discussed.     

Self‐efficacy and justice perceptions in personnel selection: A moderated mediation model

The study investigated the role of self‐efficacy (general and task‐specific) and justice perceptions in determining the expectations of success in personnel selection procedures. We hypothesized that personnel selection self‐efficacy mediated the relationship between general self‐efficacy and outcome expectations, and that justice perceptions moderated these relationships. Our sample consisted of 206 respondents who had just graduated or were about to graduate and had previous experience in selection procedures. The moderated mediation model indicated that personnel selection self‐efficacy mediated the relationship between general self‐efficacy and outcome expectations, but only in the case of high justice perceptions, whereas general self‐efficacy had a direct effect on outcome expectations only in the case of low justice perceptions. The findings encourage more research on applicants’ expectations.     

The role of career adaptability in predicting entrepreneurial intentions: A moderated mediation model

Guided by the Career Construction Theory (Savickas, 2013), we view entrepreneurship as an adaptive vocational behavior driven by an individual's self-regulatory capacity to thrive in a complex entrepreneurial career context. Our research model posited that individuals rely on their adaptive resources and entrepreneurial self-efficacy as they form entrepreneurial intentions. Career adaptability, as self-regulatory competencies, is further strengthened by prior exposure to family business. We collected data over three measurement periods from Serbian business students (n = 380) and validated the Career Adapt-Abilities Scale (CAAS). The moderated mediation model was supported and as predicted: (a) career adaptability was positively associated with entrepreneurial intentions and (b) the mediated relationship between career adaptability and entrepreneurial intentions via entrepreneurial self-efficacy was stronger for individuals with prior exposure to family business. In addition, we provide evidence for the psychometric properties of CAAS by examining its internal consistency, test–retest reliability, and factor structure. Taken together, our study offers the groundwork for understanding successful adaptation in the entrepreneurial career context and supports the cross-national measurement equivalence and utility of CAAS in a developing economy.