A statistical method for synthesizing mediation analyses using the product of coefficient approach across multiple trials

Mediation analysis often requires larger sample sizes than main effect analysis to achieve the same statistical power. Combining results across similar trials may be the only practical option for increasing statistical power for mediation analysis in some situations. In this paper, we propose a method to estimate: (1) marginal means for mediation path a, the relation of the independent variable to the mediator; (2) marginal means for path b, the relation of the mediator to the outcome, across multiple trials; and (3) the between-trial level variance–covariance matrix based on a bivariate normal distribution. We present the statistical theory and an R computer program to combine regression coefficients from multiple trials to estimate a combined mediated effect and confidence interval under a random effects model. Values of coefficients a and b, along with their standard errors from each trial are the input for the method. This marginal likelihood based approach with Monte Carlo confidence intervals provides more accurate inference than the standard meta-analytic approach. We discuss computational issues, apply the method to two real-data examples and make recommendations for the use of the method in different settings.     

Some limitation on stein's phenomenon

We show that Stein's phenomenon is impossible for the following decision setting: the parameter space is compact, the loss function is the sum of coordinatewise strictly convex continuous loss functions, and the probability density function having the same support for every parameter θ is continuous in θ. Therefore, any coordinatewise admissible decision rule is admissible.     

Biodiversity of ant species along a disturbance gradient in residential environments of Puerto Rico

One of the most effective ways to describe the successional gradient of an environment is by using measures of biodiversity. We investigated the biodiversity of ant communities (known tramp/structure invaders) in an environment undergoing urban succession to characterize how ant communities changed along a disturbance gradient. Ant community dynamics were examined within three Puerto Rican housing developments of different ages. Within each development, we assessed the ant community using biodiversity measures of richness, abundance, diversity and evenness. We also studied changes in biodiversity within each development over time as well as how biodiversity related to food preferences within the ant communities. In general, the biodiversity measures increased as the age of the housing development increased. Monthly changes in biodiversity indicated that month was a better predictor of biodiversity in the most recently disturbed development, while the biodiversity in the older developments was less predictable from month to month. The biodiversity measures also suggested that the ant community in the youngest development was comprised mostly of generalist feeders. However, the older sites’ ant species appeared to have more specific feeding preferences. Based on the biodiversity measures of these ant communities, our findings suggest that the housing developments of different ages represented advancing stages of secondary succession. Furthermore, this study indicated that the succession of ant species occurs rapidly (<10 years) in urban environments, resulting in a relatively diverse ant community.     

Variability in the Inter‐group Attitudes of White Children: What We Can Learn from Their Ethnic Identity Labels

The current study examined the ethnic identity of White (N = 120), Latino (N = 87), and African‐American (N = 65) children and early adolescents (aged = 9–14 years), with an emphasis on whether the specific ethnic label White children used to describe themselves might reflect differences in their inter‐group attitudes and whether those differences mirror group differences between White children and children in ethnic minority groups. Results indicated that White children who identified with a minority label (i.e., White biracial, hyphenated American, ethnic/cultural/religious label) had more positive ethnic identities, were more aware of discrimination, and were less likely to show biases in their perceived similarity to in‐group and out‐group peers than youth who identified as White or American. In many instances, White children who identified with a minority label did not differ from ethnic minority youth. In addition, although all participants were more positive about their ethnic in‐group than out‐groups, children who identified their ethnicity as American were less positive about out‐groups relative to other children. Taken together, the findings indicate that children's self‐chosen ethnic identity is as important as their ascribed ethnic or racial identity in predicting their inter‐group attitudes.     

Designing a social security pension system

Abstract   This paper looks at potential models of social security pension systems. It refers often to the systems that exist in the United States and Canada (the latter more particularly) to outline the issues involved in attempting to design a "good" social security pension system. Of course, one of the issues is the definition of "good". This paper will use criteria such as poverty alleviation, retirement income adequacy, benefit/contribution sustainability, income equality and wealth distribution. In the course of the discussion, the reader will be exposed to many issues that need to be addressed in the establishment of any social security pension system in the world. This may prove to be helpful in countries where new systems are established (and even for evolving systems). It is also hoped that future students of social security will find this paper helpful in that it is meant to lay out some basic principles consistent with good social security pension design.     

They might be giants: a review of small presses and little magazines: an interview with Whitney Pastorek,Editor of Pindeldyboz

Abstract

This installment of “They Might Be Giants” highlights a small online/print zine from New York called Pindeldyboz. Described by its editor Whitney Pastorek as a lit mag, Pindeldyboz publishes new fiction every week or so at the Web site but then publishes longer fiction once a year in the annual print zine of the same name. While this may indicate a split personality on the part of the editor/publisher, the goals of both the print and online versions are the same: to publish good fiction.     

Use of robust estimators of missing data in evaluating shiftwork performance

Abstract

Major problems apparent in studies evaluating the performance of employees across a large number of shifts often involve data missing due to a lack of employee participation in all possible shifts, and large variance around central tendency estimators owing to extreme responses on performance measures. These problems and possible solutions are considered here with reference to a data set collected from a number of shiftworkers in the steel industry. Data were collected from 28 employees over a morning shift and night-shift roster. The shift consisted of two cycles of MORNING-MORNING-NIGHT-NIGHT. The employees were male computer operators working a 12-h shift. The work required them to be constantly alert, and to read, monitor and respond to messages from multiple media channels. Included in the test battery were five performance indicators of cognitive speed and power. This battery was delivered using two IBM computers, which controlled the sequences and administration of the cognitive tasks. Administration of the battery was conducted in the work room and undertaken as close as possible to starting work, and as close as possible to completing work. The findings indicate that regression modelling was the most efficient way of estimating missing data. The use of M-estimators reduced the influence of extreme values on parameter estimation, and increased effect size over that observed using raw data.