RMediation: An R package for mediation analysis confidence intervals

By Davood Tofighi, David P. MacKinnon. Behavior Research Methods, 2011

1,405 citations recorded by the source corpus.

This article describes the RMediation package,which offers various methods for building confidence intervals (CIs) for mediated effects. The mediated effect is the product of two regression coefficients. The distribution-of-the-product method has the best statistical performance of existing methods for building CIs for the mediated effect. RMediation produces CIs using methods based on the distribution of product, Monte Carlo simulations, and an asymptotic normal distribution. Furthermore, RMediation generates percentiles, quantiles, and the plot of the distribution and CI for the mediated effect. An existing program, called PRODCLIN, published in Behavior Research Methods, has been widely cited and used by researchers to build accurate CIs. PRODCLIN has several limitations: The program is somewhat cumbersome to access and yields no result for several cases. RMediation described herein is based on the widely available R software, includes several capabilities not available in PRODCLIN, and provides accurate results that PRODCLIN could not.

Subfields: Applied Psychology, Developmental and Educational Psychology, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/c23b7aec27bf59eab2d3fb0691003af144f0dc5e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Psychology

In Developmental and Educational Psychology

In Experimental and Cognitive Psychology

Citations in the corpus

Multilevel Mediation With Small Samples: A Cautionary Note on the Multilevel Structural Equation Modeling Framework (2017, background): “We do not delve into the mathematical details here because they are intricate and are beyond the scope of this article, but full details can be found in MacKinnon et al. (2007) or Tofighi and MacKinnon (2011), among others.”
Are Robust Standard Errors the Best Approach for Interval Estimation With Nonnormal Data in Structural Equation Modeling? (2018, methodology): “In particular, we used RMediation (Tofighi & MacKinnon, 2011) using either normal theory (MC) or robust (R-MC) versions ofΩ.”
Peer victimization and suicidality among LGBTQ youth: the roles of school belonging, self-compassion, and parental support (2018, methodology): “This technique utilizes a distribution-of-product method to evaluate significance levels of the indirect effects by estimating a 95% CI (Tofighi & MacKinnon, 2011).”
Socioeconomic status and executive function: developmental trajectories and mediation. (2015, methodology): “The significance of the indirect pathway ^ a ^ b was assessed by building 95% confidence intervals (CIs) in RMediation using the distribution of the product method (MacKinnon , 2008; Tofighi & MacKinnon, 2011).”
Monte Carlo Confidence Intervals for Complex Functions of Indirect Effects (2016, methodology): “Although both the Monte Carlo and asymptotic–delta methods use summary analysis and are flexible in handling SEM, the Monte Carlo method produces more accurate results, especially for smaller sample sizes (MacKinnon et al., 2004; Tofighi & MacKinnon, 2011).”
Examining Social Class and Work Meaning Within the Psychology of Working Framework (2014, methodology): “AMOS 18 does not test individual indirect effects for each mediator, so we used RMediation, which uses the distribution of product coefficients method to generate CIs for specific indirect effects (Tofighi & MacKinnon, 2011).”
Social support at work and at home: Dual-buffering effects in the work-family conflict process (2018, background): “Such resources may come in the form of positive affect that is induced by supportive interactions at home (Watson, 2000), and positive affect can enable employees to more effectively perform their family role. Indeed, in a daily study, Ilies and colleagues (2007) found that on evenings when they exp”
Unmasking the creative self-efficacy–creative performance relationship: the roles of thriving at work, perceived work significance, and task interdependence (2020, methodology): “…product of coefficients to determine the indirect effect given that this method is more accurate in terms of Type I error rates, has greater power than other tests, and is one of the best methods for determining CIs for mediated effects (MacKinnon, Coxe, & Baraldi, 2012; Tofighi & MacKinnon, 2011).”
Psychological and social factors associated with wastewater reuse emotional discomfort (2015, methodology): “Finally, regression equations, along with the PRODCLIN program (Tofighi & MacKinnon, 2011) were used to explore the three hypothesized mediation models.”
Two-condition within-participant statistical mediation analysis: A path-analytic framework. (2017, methodology): “Alternatively, a Monte Carlo confidence interval (see, e.g., Preacher & Selig, 2012) could be constructed using various resources available online, including existing code for R, SPSS, or SAS (e.g., Hayes, 2013; Appendix B; Tofighi & MacKinnon, 2011).”