A Comparison of Single Sample and Bootstrap Methods to Assess Mediation in Cluster Randomized Trials

Pituch, Keenan A.; Stapleton, Laura M.; Kang, Joo Youn

doi:10.1207/s15327906mbr4103_5

Cited by 119 publications

(115 citation statements)

References 27 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…Compared with traditional approaches for testing mediation, which are inappropriate for nested data (22), the PRODCLIN method provides more power and more accurate type I error rates for single-level and multilevel designs (23)(24)(25). As predicted, the indirect path through aggressive impulses was statistically significant because the 95% CI (−0.003 to −0.0002) excluded the value zero.…”

Section: Resultsmentioning

confidence: 85%

Low glucose relates to greater aggression in married couples

Bushman

DeWall

Pond

et al. 2014

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Intimate partner violence affects millions of people globally. One possible contributing factor is poor self-control. Self-control requires energy, part of which is provided by glucose. For 21 days, glucose levels were measured in 107 married couples. To measure aggressive impulses, each evening participants stuck between 0 and 51 pins into a voodoo doll that represented their spouse, depending how angry they were with their spouse. To measure aggression, participants competed against their spouse on a 25-trial task in which the winner blasted the loser with loud noise through headphones. As expected, the lower the level of glucose in the blood, the greater number of pins participants stuck into the voodoo doll, and the higher intensity and longer duration of noise participants set for their spouse.Quarrel not at all. No man resolved to make the most of himself can spare time for personal contention. Still less can he afford to take all the consequences, including the vitiating of his temper and loss of self control. Abraham LincolnA s former US President Abraham Lincoln notes, quarrels and contentions not only waste time, they can also produce harmful consequences, such as damaging relationships. It is somewhat ironic that such quarrels and contentions often occur between people who are closest to each other: intimate partners. Sometimes these "lovers' quarrels" can escalate beyond hurtful words to physical acts of aggression and violence. Intimate partner violence refers to physical, sexual, or psychological harm caused by a partner or spouse (1). Intimate partner violence affects millions of people around the world (2). As Lincoln suggests, loss of self-control may help explain why people quarrel and contend with others, even their intimate partners. Self-ControlSelf-control refers to the ability to override an urge, desire, impulse, or habitual tendency (3). In intimate relationships, it is especially important to keep angry feelings in check. The need to vent one's anger is one of the most frequently cited motivations for intimate partner violence among male and female perpetrators (4). Unfortunately, people have fewer and less effective techniques for controlling anger than for controlling any other emotion (5). To override an aggressive urge, self-control is needed.However, self-control is not an unlimited resource. When people use self-control energy, it becomes depleted, an effect called "ego depletion" (6). Numerous studies have shown that when people engage in one act of self-control, they have less selfcontrol for subsequent tasks (3). Of particular relevance to the present study is research showing that when people engage in an initial act of self-control, they are less able to subsequently control their aggressive impulses (7). Overriding aggressive impulses requires self-control energy, and, when some of that energy is depleted, people become more aggressive.Self-control requires energy, and that energy is provided in part by glucose. Glucose is made from nutritious intake that becomes converted i...

show abstract

Section: Resultsmentioning

confidence: 85%

Low glucose relates to greater aggression in married couples

Bushman

DeWall

Pond

et al. 2014

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…The MC method was first applied to the mediation context by MacKinnon et al (2004) and is closely related to the empirical-M method (MacKinnon et al, 2002(MacKinnon et al, , 2004Pituch & Stapleton, 2008;Pituch et al, 2006;Pituch, Whittaker, & Stapleton, 2005), especially as generalized by Williams and MacKinnon (2008) to cases beyond single-mediator models. The MC method relies on the assumption that the parameters a and b have a joint normal sampling distribution, with parameters supplied by (often, but not necessarily) maximum likelihood estimates from the fitted parametric model:…”

Section: The Monte Carlo Methodsmentioning

confidence: 99%

“…The RB bootstrap has been used to assess mediation in multilevel models (Pituch, Stapleton, & Kang, 2006) but has only recently been suggested for use in the more common single-level mediation models (Zhang & Wang, 2008). The version of the RB bootstrap used in our simulation is identical to that of Zhang and Wang and similar to that of Pituch et al, except that residuals were obtained via bootstrapping rather than through Monte Carlo simulation.…”

Section: Residual-based Bootstrapmentioning

confidence: 99%

Advantages of Monte Carlo Confidence Intervals for Indirect Effects

Preacher

Selig²

2012

Communication Methods and Measures

1,515

1,104

View full text Add to dashboard Cite

Monte Carlo simulation is a useful but underutilized method of constructing confidence intervals for indirect effects in mediation analysis. The Monte Carlo confidence interval method has several distinct advantages over rival methods. Its performance is comparable to other widely accepted methods of interval construction, it can be used when only summary data are available, it can be used in situations where rival methods (e.g., bootstrapping and distribution of the product methods) are difficult or impossible, and it is not as computer-intensive as some other methods. In this study we discuss Monte Carlo confidence intervals for indirect effects, report the results of a simulation study comparing their performance to that of competing methods, demonstrate the method in applied examples, and discuss several software options for implementation in applied settings.In its simplest form, mediation occurs when the effect of an independent variable (X) on a dependent variable (Y) is transmitted via a mediator variable (M) (see Figure 1).1 This mediation effect is also commonly referred to as the indirect effect of X on Y through M. Mediation models permit researchers to test simple hypotheses about how causal processes may occur and form the building blocks of more complicated structural models. Mediation models often involve parsing the total effect (c) of X on Y into a direct effect (c ) and an indirect effect (a × b, or simply ab). These coefficients can be derived from fitting the following simultaneous equations to sample data using linear regression or path analysis, with straightforward extensions to latent variable models:Figure 1 depicts these effects using simple path diagrams of the effect of X on Y both without and with M included in the model. In mediation analysis, attention focuses mostly on the indirect 1 In order for the results of a mediation analysis to have a causal interpretation, several additional assumptions must be met.

show abstract

“…A bias-corrected residual-based bootstrap method was implemented in SAS by Pituch et al (2006) for the conflated model for 2-1-1 data. However, as of this writing, there is no software that can perform both MSEM and the nonparametric bootstrap.…”

Section: Implementation Issuesmentioning

confidence: 99%

“…For example, some authors have discussed models in which the independent variable X, mediator M, and dependent variable Y all are measured at Level 1 of a two-level hierarchy (a 1-1-1 design, adopting notation proposed by Krull & MacKinnon, 2001), 1 and slopes either are fixed (Pituch, Whittaker, & Stapleton, 2005) or are permitted to vary across Level-2 units (Bauer, Preacher, & Gil, 2006;Kenny, Korchmaros, & Bolger, 2003). Other mediation models have also been examined, including mediation in 2-2-1 designs, in which both X and M are assessed at the group level (Krull & MacKinnon, 2001;Pituch, Stapleton, & Kang, 2006), and mediation in 2-1-1 designs, in which only X is assessed at the group level (Krull & MacKinnon, 1999Pituch & Stapleton, 2008;Raudenbush & Sampson, 1999).Each of these approaches from the MLM literature was suggested in response to the need to estimate a particular model to test a mediation hypothesis in a specific design. However, the MLM paradigm is unable to accommodate simultaneous estimation of a 1 We slightly alter the purpose of Krull and MacKinnon's (2001) notation to refer to data collection designs rather than to models.…”

mentioning

confidence: 99%

A general multilevel SEM framework for assessing multilevel mediation.

Preacher

Zyphur

Zhang

2010

Psychological Methods

3,083

3,051

View full text Add to dashboard Cite

Several methods for testing mediation hypotheses with 2-level nested data have been proposed by researchers using a multilevel modeling (MLM) paradigm. However, these MLM approaches do not accommodate mediation pathways with Level-2 outcomes and may produce conflated estimates of between-and within-level components of indirect effects. Moreover, these methods have each appeared in isolation, so a unified framework that integrates the existing methods, as well as new multilevel mediation models, is lacking. Here we show that a multilevel structural equation modeling (MSEM) paradigm can overcome these 2 limitations of mediation analysis with MLM. We present an integrative 2-level MSEM mathematical framework that subsumes new and existing multilevel mediation approaches as special cases. We use several applied examples and accompanying software code to illustrate the flexibility of this framework and to show that different substantive conclusions can be drawn using MSEM versus MLM. Researchers in behavioral, educational, and organizational research settings often are interested in testing mediation hypotheses with hierarchically clustered data. For example, Bacharach, Bamberger, and Doveh (2008) investigated the mediating role of distress in the relationship between the intensity of involvement in work-related incidents and problematic drinking behavior among firefighting personnel. They used data in which firefighters were nested within ladder companies and all three variables were assessed at the subject level. Using data from customer service engineers working in teams, Maynard, Mathieu, Marsh, and Ruddy (2007) found that team-level interpersonal processes mediate the relationship between team-level resistance to empowerment and individual job satisfaction. Both of these examples-and many others-involve data that vary both within and between higher level units. Traditional methods for assessing mediation (e.g., Baron & Kenny, 1986;MacKinnon, Lockwood, Hoffman, West, & Sheets, 2002;MacKinnon, Warsi, & Dwyer, 1995) are inappropriate in these multilevel settings, primarily because the assumption of independence of observations is violated when clustered data are used, leading to downwardly biased standard errors if ordinary regression is used. For this reason, several methods have been proposed for addressing mediation hypotheses when the data are hierarchically organized.These recommended procedures for testing multilevel mediation have been developed and framed almost exclusively within the standard multilevel modeling (MLM) paradigm (for thorough treatments of MLM, see Bryk, 2002, andSnijders &Bosker, 1999) and implemented with commercially available MLM software, such as SAS PROC MIXED, HLM, or MLwiN. For example, some authors have discussed models in which the independent variable X, mediator M, and dependent variable Y all are measured at Level 1 of a two-level hierarchy (a 1-1-1 design, adopting notation proposed by Krull & MacKinnon, 2001), 1 and slopes either are fixed (Pituch, Whittaker, & Stapleton, 2005...

show abstract

A Comparison of Single Sample and Bootstrap Methods to Assess Mediation in Cluster Randomized Trials

Cited by 119 publications

References 27 publications

Low glucose relates to greater aggression in married couples

Low glucose relates to greater aggression in married couples

Advantages of Monte Carlo Confidence Intervals for Indirect Effects

A general multilevel SEM framework for assessing multilevel mediation.

Contact Info

Product

Resources

About