Digital Module 06: Bayesian Psychometrics—Posterior Predictive Model Checking https://ncme.elevate.commpartners.com

Drawing valid inferences from modern measurement models is contingent upon a good fit of the data to the model. Violations of model‐data fit have numerous consequences, limiting the usefulness and applicability of the model. As Bayesian estimation is becoming more common, understanding the Bayesian approaches for evaluating model‐data fit models is critical. In this instructional module, Allison Ames and Aaron Myers provide an overview of Posterior Predictive Model Checking (PPMC), the most common Bayesian model‐data fit approach. Specifically, they review the conceptual foundation of Bayesian inference as well as PPMC and walk through the computational steps of PPMC using real‐life data examples from simple linear regression and item response theory analysis. They provide guidance for how to interpret PPMC results and discuss how to implement PPMC for other model(s) and data. The digital module contains sample data, SAS code, diagnostic quiz questions, data‐based activities, curated resources, and a glossary.     

Coordinating a Large,Amalgamated REU Program with Multiple Funding Sources

Abstract

In this paper, we discuss the challenges of organizing a large REU program amalgamated from multiple funding sources, including diverse participants, mentors, and research projects. We detail the program’s structure, activities, and recruitment, and we hope to demonstrate that the organization of this REU is not only beneficial to its participants, but that these ideas can be adapted to the benefit of participants at other REU sites, regardless of the size or structure of the site.     

The Use of Relational Maintenance Behaviors and Relational Characteristics Among Sibling Types

The purpose of this investigation is to apply Gold's (1989 Gold, D. T. (1989). Sibling relationships in old age: A typology. International Journal of Aging and Human Development, 28, 37–51.[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]) typology of sibling relationships to the study of adult-sibling use of relational maintenance behaviors and perceptions of relational characteristics. Participants were 196 adults who targeted a sibling whose birthday was closest to their own and completed a series of instruments in reference to the targeted sibling. It was found that whether individuals classified their sibling relationships as intimate, congenial, loyal, or apathetic/hostile was reflected in their self-reported use of relational maintenance behaviors, their perceptions of their targeted siblings' use of relational maintenance behaviors with them, and their perceptions of the relational characteristics associated with the sibling relationship.     

A modified incremental shuttle run test for the determination of peak shuttle running speed and the prediction of maximal oxygen uptake.

The aim of this study was to determine the incidence of subject drop-out on a multi-stage shuttle run test and a modified incremental shuttle run test in which speed was increased by 0.014 m x s(-1) every 20-m shuttle to avoid the need for verbal speed cues. Analysis of the multi-stage shuttle run test with 208 elite female netball players and 381 elite male lacrosse players found that 13 (+/-3) players stopped after the first shuttle of each new level, in comparison with 5 (+/-2) players on any other shuttle. No obvious drop-out pattern was observed on the incremental shuttle run test with 273 male and 79 female undergraduate students. The mean difference between a test-retest condition (n = 20) for peak shuttle running speed (-0.03+/-0.01 m x s(-1)) and maximal heart rate (0.4+/-0.1 beats x min(-1)) on the incremental test showed no bias (P > 0.05). The 95% absolute confidence limits of agreement were+/-0.11 m x s(-1) for peak shuttle running speed and+/-5 beats min(-1) for maximal heart rate. The relationship (n = 27) between peak shuttle running speed on the incremental shuttle run test (4.22+/-0.14 m x s(-1)) and VO2max (59.0+/-1.7 ml kg(-1) x min(-1)) was r= 0.91 (P< 0.01), with a standard error of prediction of +/-2.6 ml x kg(-1) x min(-1). These results suggest verbal cues during the multi-stage shuttle run test may influence subject drop-out. The incremental shuttle run test shows no obvious drop-out patten and provides a valid estimate of VO2max.     

Athletes' evaluations of their head coach's coaching competency

This study provided initial validity evidence for multidimensional measures of coaching competency derived from the Coaching Competency Scale (CCS). Data were collected from intercollegiate men's (n = 8) and women's (n = 13) soccer and women's ice hockey teams (n = 11). The total number of athletes was 585. Within teams, a multidimensional internal model was retained in which motivation, game strategy, technique, and character building comprised the dimensions of coaching competency. Some redundancy among the dimensions was observed. Internal reliabilities ranged from very good to excellent. Practical recommendations for the CCS are given in the Discussion section.     

The utility of kindergarten teacher ratings for predicting low academic achievement in first grade

The purpose of this study was to assess the predictive value of kindergarten teachers' ratings of pupils for later first-grade academic achievement. Kindergarten students were rated by their teachers on a variety of variables, including math and reading performance, teacher concerns, and amount of learning relative to peers. These variables were then analyzed with respect to outcome measures for math and reading ability administered in the first grade. The teachers' ratings of academic performance were significantly correlated with scores on the outcome measures. Analyses were also carried out to determine sensitivity, specificity, and predictive values of the different teacher ratings. The results indicated high overall accuracy, sensitivity, specificity, and negative predictive value for the ratings. Positive predictive value tended to be lower. A recommendation to follow from these results is that teacher ratings of this sort be used to determine which children should receive cognitive screening measures to further enhance identification of children at risk for learning disability. However, this recommendation is limited by the lack of empirically supported screening measures for math disability versus well-supported screening tools for reading disability.     

Long-Term Memory for a Single Infancy Experience

Children's memory of a single infant experience was evaluated. Children in the experimental groups (N = 16 for 2.5-year-olds; N = 8 for 1.5-year-olds) had participated at 6.5 months in a study of auditory localization where they reached in the light and dark for a sounding object. They were reintroduced to the laboratory and the dark procedure they had experienced on that one occasion either 1 or 2 years previously. The first 5 trials were uninstructed; for the remaining 5 trials, children were instructed to find the sounding object. For half of the older group, a potential reminder of the infant procedure was introduced. The original infant rattle was sounded for 3 sec out of reach in the dark one-half hour prior to test trials. Equal numbers of age-matched inexperienced control subjects were also tested. The older children with infant experience reached and grasped the sounding object significantly more overall, and on instructed trials, than age-matched control children. Experienced 2.5-year-olds were also more likely to remain in the testing situation than children in the control group. The reminder facilitated uninstructed performance of the experienced children. Instructions to reach were helpful to all subjects. We conclude that children remembered aspects of a single experience that occurred when they were 6.5 months of age.     

The impact of peer support schemes on pupils' perceptions of bullying,aggression and safety at school

The research was carried out in four secondary schools, two with a peer support system and two without, and involved a total of 931 pupils (49.5% males and 50.5% females). Participants were aged between 11 and 15 years of age, mean age 12.8 years. The aims were: to compare the perceptions of safety on the part of older and younger pupils in secondary schools with and without a system of peer support in place; to find out if there are differences in perceptions of safety within peer support schools on the part of those who are aware of the existence of a peer support service in their school and those who are not aware; and to find out if pupils in peer support schools are more likely to tell someone about school violence and bullying than those in schools without peer support. The results indicate very little difference between pupil perceptions of safety in schools with and schools without a peer support system in place. In fact, older pupils in the schools without peer support responded that they felt safer than pupils in schools with a peer support system in toilets and lessons. However, within the peer support schools there were significant differences in perceptions of safety between the substantial minority of pupils who were unaware that their school had a peer support system and those who were aware of it. The pupils who were aware felt safer in lessons, perceived school as a friendlier place to be, and worried significantly less about being bullied in comparison with those who were unaware. They were also much more likely to tell someone when bad things happened at school. The results are discussed in the light of previous research in the field and some recommendations are made for the practice of peer support.