A graphical representation of the mediated effect

Mediation analysis is widely used in the social sciences. Despite the popularity of mediation models, few researchers have used graphical methods, other than structural path diagrams, to represent their models. Plots of the mediated effect can help a researcher better understand the results of the analysis and convey these results to others. This article presents a method for creating and interpreting plots of the mediated effect for a variety of mediation models, including models with (1) a dichotomous independent variable, (2) a continuous independent variable, and (3) an interaction between an independent variable and the mediating variable. An empirical example is then presented to illustrate these plots. Sample code for creating plots of the mediated effect in R and SAS is also included, and may be downloaded from www.psychonomic.org/archive.     

Covariances between regression coefficient estimates in a single mediator model

This study presents formulae for the covariances between parameter estimates in a single mediator model. These covariances are necessary to build confidence intervals (CI) for effect size measures in mediation studies. We first analytically derived the covariances between the parameter estimates in a single mediator model. Using the derived covariances, we computed the multivariate‐delta standard errors, and built the 95% CIs for the effect size measures. A simulation study evaluated the accuracy of the standard errors as well as the Type I error, power, and coverage of the CIs using various parameter values and sample sizes. Finally, we presented a numerical example and a SAS MACRO that calculates the CIs for the effect size measures.     

A Comparison Between Mexican American Youth Who Are in Gangs and Those Who Are Not

This exploratory study compares the differences between 43 Mexican American gang members and 43 Mexican American adolescents who are not members of a gang on several demographic, educational, familial, cultural, and psychological variables. Differences were analyzed using t tests and chi‐square analyses. Discussion focuses on implications for counseling. Este estudio de exploración compara las diferencias entre 43 Mexicoamericanos pertenecientes a alguna pandilla y 43 adolescentes Mexicoamericanos que no son miembros de una pandilla según distintas variables demográficas, educativas, familiares, culturales y psicológicas. Las diferencias se analizaron usando pruebas t y análisis de ji‐cuadrado. La discusión se centra en las implicaciones para la consejería.     

A Bayesian Approach for Estimating Mediation Effects With Missing Data

Methodologists have developed mediation analysis techniques for a broad range of substantive applications, yet methods for estimating mediating mechanisms with missing data have been understudied. This study outlined a general Bayesian missing data handling approach that can accommodate mediation analyses with any number of manifest variables. Computer simulation studies showed that the Bayesian approach produced frequentist coverage rates and power estimates that were comparable to those of maximum likelihood with the bias-corrected bootstrap. We share an SAS macro that implements Bayesian estimation and use 2 data analysis examples to demonstrate its use.     

The Distribution of the Product Explains Normal Theory Mediation Confidence Interval Estimation

The distribution of the product has several useful applications. One of these applications is its use to form confidence intervals for the indirect effect as the product of 2 regression coefficients. The purpose of this article is to investigate how the moments of the distribution of the product explain normal theory mediation confidence interval coverage and imbalance. Values of the critical ratio for each random variable are used to demonstrate how the moments of the distribution of the product change across values of the critical ratio observed in research studies. Results of the simulation study showed that as skewness in absolute value increases, coverage decreases. And as skewness in absolute value and kurtosis increases, imbalance increases. The difference between testing the significance of the indirect effect using the normal theory versus the asymmetric distribution of the product is further illustrated with a real data example. This article is the first study to show the direct link between the distribution of the product and indirect effect confidence intervals and clarifies the results of previous simulation studies by showing why normal theory confidence intervals for indirect effects are often less accurate than those obtained from the asymmetric distribution of the product or from resampling methods.     

An Assessment of the Utility of Suicide Prediction*

ABSTRACT: Efforts to predict a future event assume varying levels of confidence depending on its base rate and the error rate of the prediction instrument. Most researchers working with suicide prediction instruments seem tacitly to assume they will be able to predict a future suicide most of the time. Applying basic decision theory on a neuropsychiatric hospital population indicates that researchers using a prediction schedule will be unlikely to predict a future suicide beyond a 20% level of efficiency. Contrary to the general clinical view, eliminating false negatives was shown to be more practical than eliminating false positives in increasing the efficiency of a predictive schedule.     

The Certification of Suicide in Eleven Western States: An Inquiry into the Validity of Reported Suicide Rates

ABSTRACT: From Durkheim's time to the present social researchers interested in the problem of suicide have relied upon officially reported rates of suicide to develop and test their theories. Despite the fact that the validity of any theory rests upon the accuracy of its underlying data, the relative accuracy of reported suicide rates have rarely been questioned or systematically evaluated. This paper investigates the process of death certification as practiced by a sample of 191 coroners in 11 western states. Findings indicate extensive variation in the backgrounds, professional resources, operating procedures, and governing statutes of coroners and coroners' offices and in policies concerning the use of the suicide mode. Since the coroner is generally charged with the official responsibility for certifying the mode of death when unnatural mode is suspect, the extent of variation found here calls into question the validity and comparability of reported suicide rates.     

Family–oriented treatment for people with alcohol problems in Ireland: a comparison of the effectiveness of residential and community–based programmes

Using a naturalistic design involving consecutive referrals self–selected for family–oriented treatment, forty–two participants from a residential programme and twenty–five participants from a community–based programme were assessed on a range of alcohol–use and psychosocial measures before treatment. A proportion of these cases were assessed after treatment and at six months'follow–up. At six months' follow–up 79 per cent of both the residential and community groups were either abstinent or drinking moderately. However, more members of the residential group (75 per cent) were abstinent at follow–up compared with the community group (36 per cent). In contrast, more members of the community group were moderate drinkers (43 per cent) at follow–up compared with the residential group (4 per cent). At six months' follow–up, compared with the community group, more members of the residential group showed a clinically significant reduction in recent negative consequences of drinking and psychological adjustment problems. Both groups made significant mean gains on indices of alcohol abuse and psychosocial adjustment but there were important intergroup differences. The residential group showed a greater mean reduction in recent negative consequences from drinking but the community group showed a greater mean reduction in the percentage of days' heavy drinking.     

Same-sex and cross-sex siblings: Activity choices,roles, behavior,and gender stereotypes

Forty same-sex and cross-sex school-aged sibling pairs were observed in their homes during self-selected activities. The sex role learning index (SERLI) and a sex-typing room analysis were administered for the younger siblings, and maternal questionnaire information was obtained. Sibling gender constellation was associated with reliable differences in activity choices during the unstructured observations. Male dyads interacted less than other sibling groups, while older sisters in female dyads engaged in the most teaching. Older female siblings, regardless of the gender of the younger sibling, assumed the manager role frequently. Dyads containing an older girl also exhibited the greatest role asymmetrics. Affective differences related to gender constellation were also noted. Younger girls with older brothers and younger boys with older sisters evidenced the least gender stereotyping.