Mediational Analysis in HIV/AIDS Research: Estimating Multivariate Path Analytic Models in a Structural Equation Modeling Framework

Abstract

Mediational analyses have been recognized as useful in answering two broad questions that arise in HIV/AIDS research, those of theoretical model testing and of the effectiveness of multicomponent interventions. This article serves as a primer for those wishing to use mediation techniques in their own research, with a specific focus on mediation applied in the context of path analysis within a structural equation modeling (SEM) framework. Mediational analyses and the SEM framework are reviewed at a general level, followed by a discussion of the techniques as applied to complex research designs, such as models with multiple mediators, multilevel or longitudinal data, categorical outcomes, and problematic data (e.g., missing data, nonnormally distributed variables). Issues of statistical power and of testing the significance of the mediated effect are also discussed. Concrete examples that include computer syntax and output are provided to demonstrate the application of these techniques to testing a theoretical model and to the evaluation of a multicomponent intervention.

Indirect Effects of Acute Alcohol Intoxication on Sexual Risk-taking: The Roles of Subjective and Physiological Sexual Arousal

“…Also, as hypothesized, subjective sexual arousal mediated the effects of alcohol on risk-taking; alcohol had no direct effects on risktaking. In keeping with recently published guidelines for mediational analyses in HIV/AIDS research (Bryan et al, 2007), we used structural equation modeling to evaluate our mediational hypotheses. This approach allowed us to simultaneously consider multiple mediatonal paths, ruling out paths dependent on genital arousal and bolstered confidence in the mediational effects observed.…”

“…As hypothesized, self-reported sexual arousal during the risktaking vignette significantly predicted unprotected sex likelihood, β = .47, p < .001, with estimated likelihood increasing as self-reported sexual arousal increased. In addition to direct effects, we tested the significance of indirect effects, as recommended by Bryan et al (2007). Results showed that alcohol condition had a significant indirect effect on likelihood of unprotected sex via subjective sexual arousal, β = .09, p < .05.…”

“…There were no other significant direct effects. Again following procedures recommended by Bryan et al (2007), we tested the significance of indirect effects. Results showed that alcohol condition had a significant indirect effect on likelihood of unprotected sex via subjective sexual arousal, β = .09, p < .01.…”

To Re-Explore the Causality between Barriers to Renewable Energy Development: A Case Study of Wind Energy

“…Thus the impact of national policies on the R&D capacity may be subject to change due to the PPA or fiscal incentives. In theory, we can take PPA with fiscal incentives as the mediator between P1 and T1 [5,[60][61][62][63][64][65][66]. Similarly, the theoretical model includes three mediators: R&D capacity (i.e., C1 → T1 → T3), site availability (i.e., E2 → E1 → C2), and the fundamental infrastructure (i.e., E1 → S2 → C2).…”

“…However, the theoretical model of this study contains the presence of multiple mediators (Me), which change the original relationship between the independent variables (IV) and the dependent variables (DV) from direct effect (IV → DV) into an mediating effect (IV → Me → DV) [5,61,65,66]. In the consideration of the characteristics of the SEM method, we used the co-variance among variables, simultaneously to estimate the model parameters, and to test the goodness-of-fit between the theoretical models and the observed data [54,55,60,[62][63][64]. Therefore, by considering all the reasons mentioned above, the SEM oriented path analysis was the more suitable choice of method for the study.…”