Amanda J. Fairchild

Current Directions in Mediation Analysis

Mediating variables continue to play an important role in psychological theory and research. A mediating variable transmits the effect of an antecedent variable on to a dependent variable, thereby providing more detailed understanding of relations among variables. Methods to assess mediation have been an active area of research for the last two decades. This paper describes the current state of methods to investigate mediating variables.

A General Model for Testing Mediation and Moderation Effects

This paper describes methods for testing mediation and moderation effects in a dataset, both together and separately. Investigations of this kind are especially valuable in prevention research to obtain information on the process by which a program achieves its effects and whether the program is effective for subgroups of individuals. A general model that simultaneously estimates mediation and moderation effects is presented, and the utility of combining the effects into a single model is described. Possible effects of interest in the model are explained, as are statistical methods to assess these effects. The methods are further illustrated in a hypothetical prevention program example.

The integration of a family systems approach for understanding youth obesity, physical activity, and dietary programs.

Rates of overweight in youth have reached epidemic proportions and are associated with adverse health outcomes. Family-based programs have been widely used to treat overweight in youth. However, few programs incorporate a theoretical framework for studying a family systems approach in relation to youth health behavior change. Therefore, this review provides a family systems theory framework for evaluating family-level variables in weight loss, physical activity, and dietary approaches in youth. Studies were reviewed and effect sizes were calculated for interventions that manipulated the family system, including components that targeted parenting styles, parenting skills, or family functioning, or which had novel approaches for including the family. Twenty-one weight loss interventions were identified, and 25 interventions related to physical activity and/or diet were identified. Overall, family-based treatment programs that incorporated training for authoritative parenting styles, parenting skills, or child management, and family functioning had positive effects on youth weight loss. Programs to improve physical activity and dietary behaviors that targeted the family system also demonstrated improvements in youth health behaviors; however, direct effects of parent-targeted programming is not clear. Both treatment and prevention programs would benefit from evaluating family functioning and parenting styles as possible mediators of intervention outcomes. Recommendations are provided to guide the development of future family-based obesity prevention and treatment programs for youth.

R2 effect-size measures for mediation analysis

R2 effect-size measures are presented to assess variance accounted for in mediation models. The measures offer a means to evaluate both component paths and the overall mediated effect in mediation models. Statistical simulation results indicate acceptable bias across varying parameter and sample-size combinations. The measures are applied to a real-world example using data from a team-based health promotion program to improve the nutrition and exercise habits of firefighters. SAS and SPSS computer code are also provided for researchers to compute the measures in their own data.

Investigating Validity Evidence for the Experiences in Close Relationships-Revised Questionnaire

The current study gathered internal structural validity and external criterion validity evidence for the Experiences in Close Relationships-Revised Questionnaire (ECR-R) scores. Specifically, confirmatory factor analysis of the data provided general support for the hypothesized two-factor model, and hypothesized relationships with external criteria were substantiated. However, minor model misfit and low communalities (R 2) suggested that some items may represent extraneous constructs. Further avenues of study regarding the functioning of the instrument are provided.

Evaluating mediation and moderation effects in school psychology: A presentation of methods and review of current practice

Third variable effects elucidate the relation between two other variables, and can describe why they are related or under what conditions they are related. This article demonstrates methods to analyze two third-variable effects: moderation and mediation. The utility of examining moderation and mediation effects in school psychology is described and current use of the analyses in applied school psychology research is reviewed and evaluated. Proper statistical methods to test the effects are presented, and different effect size measures for the models are provided. Extensions of the basic moderator and mediator models are also described.

A Faith-Based Community Partnership to Address HIV/AIDS in the Southern United States: Implementation, Challenges, and Lessons Learned

Though race and region are not by themselves risk factors for HIV infection, regional and racial disparities exist in the burden of HIV/AIDS in the US. Specifically, African Americans in the southern US appear to bear the brunt of this burden due to a complex set of upstream factors like structural and cultural influences that do not facilitate HIV/AIDS awareness, HIV testing, or sexual risk-reduction techniques while perpetuating HIV/AIDS-related stigma. Strategies proposed to mitigate the burden among this population have included establishing partnerships and collaborations with non-traditional entities like African American churches and other faith-based organizations. Though efforts to partner with the African American church are not necessarily novel, most of these efforts do not present a model that focuses on building the capacity of the African American church to address these upstream factors and sustain these interventions. This article will describe Project Fostering AIDS Initiatives That Heal (F.A.I.T.H), a faith-based model for successfully developing, implementing, and sustaining locally developed HIV/AIDS prevention interventions in African American churches in South Carolina. This was achieved by engaging the faith community and the provision of technical assistance, grant funding and training for project personnel. Elements of success, challenges, and lessons learned during this process will also be discussed.

A Bayesian Approach for Estimating Mediation Effects with Missing Data.

Methodologists have developed mediation analysis techniques for a broad range of substantive applications, yet methods for estimating mediating mechanisms with missing data have been understudied. This study outlined a general Bayesian missing data handling approach that can accommodate mediation analyses with any number of manifest variables. Computer simulation studies showed that the Bayesian approach produced frequentist coverage rates and power estimates that were comparable to those of maximum likelihood with the bias-corrected bootstrap. We share an SAS macro that implements Bayesian estimation and use 2 data analysis examples to demonstrate its use.

The Children and Parents in Focus project: a population-based cluster-randomised controlled trial to prevent behavioural and emotional problems in children

BackgroundThere is large body of knowledge to support the importance of early interventions to improve child health and development. Nonetheless, it is important to identify cost-effective blends of preventive interventions with adequate coverage and feasible delivery modes. The aim of the Children and Parents in Focus trial is to compare two levels of parenting programme intensity and rate of exposure, with a control condition to address impact and cost-effectiveness of a universally offered evidence-based parenting programme in the Swedish context.Methods/DesignThe trial has a cluster randomised controlled design comprising three arms: Universal arm (with access to participation in Triple P - Positive Parenting Program, level 2); Universal Plus arm (with access to participation in Triple P - Positive Parenting Program, level 2 as well as level 3, and level 4 group); and Services as Usual arm. The sampling frame is Uppsala municipality in Sweden. Child health centres consecutively recruit parents of children aged 3 to 5 years before their yearly check-ups (during the years 2013–2017). Outcomes will be measured annually. The primary outcome will be children’s behavioural and emotional problems as rated by three informants: fathers, mothers and preschool teachers. The other outcomes will be parents’ behaviour and parents’ general health. Health economic evaluations will analyse cost-effectiveness of the interventions versus care as usual by comparing the costs and consequences in terms of impact on children’s mental health, parent’s mental health and health-related quality of life.DiscussionThis study addresses the need for comprehensive evaluation of the long-term effects, costs and benefits of early parenting interventions embedded within existing systems. In addition, the study will generate population-based data on the mental health and well-being of preschool aged children in Sweden.Trial registrationISRCTN: ISRCTN16513449.

Understanding internet sex-seeking behaviour and sexual risk among young men who have sex with men: evidences from a cross-sectional study

Objective Internet sex-seeking is common among young men who have sex with men (MSM). However, research examining its association with risky sexual behaviour has produced mixed findings, possibly due to various operational definitions of internet sex-seeking which fail to account for its multi-dimensionality. This study purposed to: (1) examine if the way internet sex-seeking behaviour is operationalised influences its association with risky sexual behaviour (unprotected anal intercourse (UAI) and casual sex) and (2) determine the association of each operational definition with sexual risk. Methods We recruited 263 sexually-experienced young MSM (18–29 years) and operationalised internet sex-seeking behaviour in four ways: (i) ever used the internet to meet other men, (ii) currently own a profile on a website dedicated to meeting other men, (iii) ever physically met a man you initially met online and (iv) ever had sex with a man you met online. Using binomial regression, we examined the association of each operationalisation with UAI and casual sex. Results Only MSM who reported physically meeting a man they met online and those who ever had sex with a man they met online were more likely to report a history of UAI (p<0.05), while MSM who engaged in all forms of internet sex-seeking were more likely to engage in casual sex (p<0.05). However, the strength of these associations varied according to the mode of operationalisation. Conclusions The way internet sex-seeking is operationalised in research is differentially associated with sexual risk. Against this backdrop, the utility of these operational definitions in future research and inferences drawn from such research must be interpreted with caution. Findings have important implications for sexual health research and methodology, survey development, sexual health prevention interventions, and evaluating sexual risk among young MSM.