Tests of Mediation: Paradoxical Decline in Statistical Power as a Function of Mediator Collinearity

Beasley, T. Mark

doi:10.1080/00220973.2013.813360

Cited by 25 publications

(11 citation statements)

References 44 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because in Equation 3, in which Y is regressed on M and X , collinearity between M and X is stronger in the first sample than in the second, resulting in a larger standard error for trueB^YM·X in the first sample. This suggests that, in general, for equivalent indirect effects and all else being held equal, larger trueB^YM·X coefficients have correspondingly larger effect sizes, which is consistent with previous research examining the behavior of different specifications for indirect effects (Beasley, 2014; Fritz & MacKinnon, 2007; Fritz, Taylor, & MacKinnon, 2012; Hoyle & Kenny, 1999).…”

Section: A Novel Effect Size Measure For Mediation Analysissupporting

confidence: 89%

A novel measure of effect size for mediation analysis.

Lachowicz¹,

Preacher²,

Kelley³

2018

Psychological Methods

159

145

View full text Add to dashboard Cite

Mediation analysis has become one of the most popular statistical methods in the social sciences. However, many currently available effect size measures for mediation have limitations that restrict their use to specific mediation models. In this article, we develop a measure of effect size that addresses these limitations. We show how modification of a currently existing effect size measure results in a novel effect size measure with many desirable properties. We also derive an expression for the bias of the sample estimator for the proposed effect size measure and propose an adjusted version of the estimator. We present a Monte Carlo simulation study conducted to examine the finite sampling properties of the adjusted and unadjusted estimators, which shows that the adjusted estimator is effective at recovering the true value it estimates. Finally, we demonstrate the use of the effect size measure with an empirical example. We provide freely available software so that researchers can immediately implement the methods we discuss. Our developments here extend the existing literature on effect sizes and mediation by developing a potentially useful method of communicating the magnitude of mediation.

show abstract

Section: A Novel Effect Size Measure For Mediation Analysissupporting

confidence: 89%

A novel measure of effect size for mediation analysis.

Lachowicz¹,

Preacher²,

Kelley³

2018

Psychological Methods

159

145

View full text Add to dashboard Cite

show abstract

“…Increasingly, mediation studies in the field have utilized bootstrapping, which is a general approach to statistical inference based on random re-sampling from the observed data. In general, the traditional Baron and Kenny 14 regression-based mediation analyses has fairly limited power; bootstrapping has been widely recommended as it improves power, even in relatively small samples, and obviates concerns over violating normality assumptions 17;124 .…”

Section: Evaluating Psychosocial Contributions To Chronic Pain Outcomesmentioning

confidence: 99%

The Role of Psychosocial Processes in the Development and Maintenance of Chronic Pain

Edwards

Dworkin

Sullivan

et al. 2016

The Journal of Pain

627

544

View full text Add to dashboard Cite

The recently-proposed ACTTION-APS Pain Taxonomy provides an evidence-based, multidimensional, chronic pain classification system. Psychosocial factors play a crucial role within several dimensions of the Taxonomy. In this paper, we discuss the evaluation of psychosocial factors that influence the diagnosis and trajectory of chronic pain disorders. We review studies in individuals with a variety of persistent pain conditions, and describe evidence that psychosocial variables play key roles in conferring risk for the development of pain, in shaping long-term pain-related adjustment, and in modulating pain treatment outcomes. We consider both “general” psychosocial variables such as negative affect, childhood trauma, and social support, as well as “pain-specific” psychosocial variables that include pain-related catastrophizing, self-efficacy for managing pain, and pain-related coping. Collectively, the complexity and profound variability in chronic pain highlights the need to better understand the multidimensional array of interacting forces that determine the trajectory of chronic pain conditions.

show abstract

“…First, their study was cross-sectional in nature, which allows inferences only based on interindividual differences, whereas the current study employed a longitudinal design, which has the advantage of identifying intraindividual changes and their interrelationships (Schaie, 2005). Second, Datu and Mateo’s study used manifest variables that may be contaminated by measurement errors, and the Sobel (1982) test for examining the indirect effects, which tends to be underpowered because of potential violation of the normality assumption (e.g., Beasley, 2014; Hayes, 2009; Preacher & Hayes, 2008). The current study instead used structural equation modeling (SEM) with latent variables to account for measurement errors, and conducted the more powerful bootstrap test of mediation, which does not rely on distributional assumption.…”

Section: Presence Of Meaning In Life As a Mediatormentioning

confidence: 99%

Gratefulness and subjective well-being: Social connectedness and presence of meaning as mediators.

Liao

Weng

2018

Journal of Counseling Psychology

View full text Add to dashboard Cite

The association between gratefulness and well-being is well established; however, few studies have examined the mechanisms that underlie this association. The broaden-and-build theory (Fredrickson, 1998, 2001) posits that positive emotions broaden individuals' momentary thought-action repertoires, which serve to build personal resources that can be drawn upon during future stressful encounters. Based on this theory, the current study examined whether gratefulness, a positive emotion, would build social and cognitive resources in terms of social connectedness and presence of meaning in life (i.e., mediators), which subsequently contribute to subjective well-being (SWB). A total of 232 students participated in an online survey at 2 different time points (3 months apart). The mediational hypothesis was tested by latent change score analyses using structural equation modeling techniques. The results showed that changes in gratefulness predicted changes in social connectedness and presence of meaning in life, which, in turn, predicted changes in SWB. The study's findings provided further support for the broaden-and-build theory and suggested that gratefulness is an important positive emotion that contributes to SWB through increased social connectedness and a greater presence of meaning in life. (PsycINFO Database Record

show abstract

Tests of Mediation: Paradoxical Decline in Statistical Power as a Function of Mediator Collinearity

Cited by 25 publications

References 44 publications

A novel measure of effect size for mediation analysis.

A novel measure of effect size for mediation analysis.

The Role of Psychosocial Processes in the Development and Maintenance of Chronic Pain

Gratefulness and subjective well-being: Social connectedness and presence of meaning as mediators.

Contact Info

Product

Resources

About