A comparison of methods to test mediation and other intervening variable effects

A Monte Carlo study compared 14 methods to test the statistical significance of the intervening variable effect. An intervening variable (mediator) transmits the effect of an independent variable to a dependent variable. The commonly used R. M. Baron and D. A. Kenny (1986) approach has low statistical power. Two methods based on the distribution of the product and 2 difference-in-coefficients methods have the most accurate Type I error rates and greatest statistical power except in 1 important case in which Type I error rates are too high. The best balance of Type I error and statistical power across all cases is the test of the joint significance of the two effects comprising the intervening variable effect.     

Coping and negative appraisal as mediators between control beliefs and psychological symptoms in children of divorce

Examined control beliefs of children of divorce as predictors of their coping, negative appraisals for stressful events, and mental health problems. We tested whether coping and negative appraisal for stressful events mediated the relations between multiple dimensions of control beliefs and mental health problems. Different dimensions of control beliefs were related to different aspects of coping and negative stress appraisal. Internal control beliefs for positive events were related to both active and avoidant coping. Unknown control beliefs for positive events were related to higher active coping and higher negative appraisal. Unknown control beliefs for negative events were related to higher avoidant coping. In addition, evidence for mediation was found such that the effect of unknown control beliefs for positive events on mental health problems was mediated by negative appraisal. Implications and directions for further research are discussed.     

The Combined Effects of Measurement Error and Omitting Confounders in the Single-Mediator Model

Mediation analysis requires a number of strong assumptions be met in order to make valid causal inferences. Failing to account for violations of these assumptions, such as not modeling measurement error or omitting a common cause of the effects in the model, can bias the parameter estimates of the mediated effect. When the independent variable is perfectly reliable, for example when participants are randomly assigned to levels of treatment, measurement error in the mediator tends to underestimate the mediated effect, while the omission of a confounding variable of the mediator-to-outcome relation tends to overestimate the mediated effect. Violations of these two assumptions often co-occur, however, in which case the mediated effect could be overestimated, underestimated, or even, in very rare circumstances, unbiased. To explore the combined effect of measurement error and omitted confounders in the same model, the effect of each violation on the single-mediator model is first examined individually. Then the combined effect of having measurement error and omitted confounders in the same model is discussed. Throughout, an empirical example is provided to illustrate the effect of violating these assumptions on the mediated effect.     

Statistical properties of four effect-size measures for mediation models

This project examined the performance of classical and Bayesian estimators of four effect size measures for the indirect effect in a single-mediator model and a two-mediator model. Compared to the proportion and ratio mediation effect sizes, standardized mediation effect-size measures were relatively unbiased and efficient in the single-mediator model and the two-mediator model. Percentile and bias-corrected bootstrap interval estimates of ab/s _Y , and ab(s _X )/s _Y in the single-mediator model outperformed interval estimates of the proportion and ratio effect sizes in terms of power, Type I error rate, coverage, imbalance, and interval width. For the two-mediator model, standardized effect-size measures were superior to the proportion and ratio effect-size measures. Furthermore, it was found that Bayesian point and interval summaries of posterior distributions of standardized effect-size measures reduced excessive relative bias for certain parameter combinations. The standardized effect-size measures are the best effect-size measures for quantifying mediated effects.     

Mechanisms of hypnotic and nonhypnotic forgetting

Subjects participated in two experimental sessions designed to study laboratory-induced amnesia, one using a standard hypnosis paradigm and one using a non-hypnotic directed-forgetting paradigm. Two independent sources of variation were derived from the hypnotic amnesia data: retrieval inhibition and inhibition release. In the nonhypnotic directed-forgetting procedure, some items were cued to be forgotten shortly after presentation and some were cued to be remembered. At test, the subjects were asked to recall both the to-be-remembered and the to-be-forgotten items. Over 39% of the variance in the recall of the to-be-forgotten items could be accounted for by the inhibition and release constructs obtained with hypnosis. These relations between the two procedures were not mediated by verbal ability or cognitive style (field independence). We concluded that the mechanisms of forgetting involved in laboratory demonstrations of hypnotic and nonhypnotic amnesia are related, and the implication is that some of them are the same, namely, retrieval inhibition and inhibition release. We also argued that the possible demand characteristics that accompany the hypnosis procedure are not apparent with the nonhypnotic procedure. Therefore, the relationships observed in the present results were taken as evidence that hypnotically induced amnesia is not entirely the result of subjects' reactions to demand characteristics.