abstract: This simulation study compared the utility of various discrepancy measures within a posterior predictive model checking (PPMC) framework for detecting different types of data-model misfit in multidimensional Bayesian network (BN) models. The investigated conditions were motivated by an applied research program utilizing an operational complex performance assessment within a digital-simulation educational context grounded in theories of cognition and learning. BN models were manipulated along two factors: latent variable dependency structure and number of latent classes. Distributions of posterior predicted p-values (PPP-values) served as the primary outcome measure and were summarized in graphical presentations, by median values across replications, and by proportions of replications in which the PPP-values were extreme. An effect size measure for PPMC was introduced as a supplemental numerical summary to the PPP-value. Consistent with previous PPMC research, all investigated fit functions tended to perform conservatively, but Standardized Generalized Dimensionality Discrepancy Measure (SGDDM), Yen's Q3, and Hierarchy Consistency Index (HCI) only mildly so. Adequate power to detect at least some types of misfit was demonstrated by SGDDM, Q3, HCI, Item Consistency Index (ICI), and to a lesser extent Deviance, while proportion correct (PC), a chi-square-type item-fit measure, Ranked Probability Score (RPS), and Good's Logarithmic Scale (GLS) were powerless across all investigated factors. Bivariate SGDDM and Q3 were found to provide powerful and detailed feedback for all investigated types of misfit. / Dissertation/Thesis / Ph.D. Educational Psychology 2014

To control various response biases and rater errors in noncognitive assessment, multidimensional forced choice (MFC) measures have been proposed as an alternative to single-statement Likert-type scales. Historically, MFC measures have been criticized because conventional scoring methods can lead to ipsativity problems that render scores unsuitable for inter-individual comparisons. However, with the recent advent of classical test theory and item response theory scoring methods that yield normative information, MFC measures are surging in popularity and becoming important components of personnel and educational assessment systems. This dissertation presents developments concerning a GGUM-based MFC model henceforth referred to as the GGUM-RANK. Markov Chain Monte Carlo (MCMC) algorithms were developed to estimate GGUM-RANK statement and person parameters directly from MFC rank responses, and the efficacy of the new estimation algorithm was examined through computer simulations and an empirical construct validity investigation. Recently derived GGUM-RANK item information functions and information indices were also used to evaluate overall item and test quality for the empirical study and to give insights into differences in scoring accuracy between two-alternative (pairwise preference) and three-alternative (triplet) MFC measures for future work. This presentation concludes with a discussion of the research findings and potential applications in workforce and educational setting.

Multilevel datasets are commonly used and increasingly popular in research in the organizational and other social sciences. These models are complex and have many elements beyond those found in more traditional linear models. However, research on how multilevel models perform is lacking. The current paper examined the impact of common factors (average cluster size, cluster size distribution, average number of clusters, strength of the intraclass correlation coefficient, and effect sizes of individual and cluster level variables, and their interaction) in multilevel datasets. Monte Carlo data simulation was used across 6,144 factor-combination conditions. The results of study factors on observed intraclass correlation coefficients, calculated design effect, and empirical design effect are discussed. The results of this study have implications for both researchers in both academic and applied fields. The scale of the simulation variables allow it to be germane to datasets from across the social sciences. However, the nature of data simulation and analysis is such that there are still many elements that can and should be accounted for in future research.

No description available.

The problem of co-occurring substance abuse and mental health disorders among the veteran population can impact numerous aspects of a veteran's life, including self-esteem, relationships, employment, and legal issues. The Mental Health Residential Rehabilitation Treatment Program (MH RRTP) at the Saint Cloud, Minnesota VA Healthcare System is a program that provides residential treatment for this population. Identifying practical and beneficial treatment methods promotes better coping mechanisms for veterans and impacts social change by providing timely and cost-efficient care for veterans, while also leading the way for overall changes and improvements in other VA residential treatment programs. This study identified how using the integrated treatment model in the MH RRTP impacted depression, anxiety, and sobriety protective factors among 1,136 veterans who completed the program between 2016 and 2017, and if there were any significant differences in outcomes among various age groups and lengths of stay in the program. Outcome measures taken at pre and post treatment, using BDI-II, BAI, and BAM, were analyzed by using six one-within one-between (mixed-model) Analysis of Variance (ANOVA) tests. Significant interaction effects were noted for protective factors in length of stay and age group categories and for depression and length of stay. Significant main effects for within-subjects factors were consistently noted for all categories, indicating a reduction in depression and anxiety symptoms, while increasing protective factors for the veterans in this study. The results demonstrated that veterans responded favorably without regard to potential differences in age groups and lengths of stay.

Numerous safety studies suggest that stress complacency related accidents in manufacturing industries continue to cause injuries or fatalities because of the absence of emotional resources for leaders, who are unable to prevent accidents when these conditions exist. Leaders of the manufactory industries may not have the appropriate emotional measures which are significant to recognize employees' underlying complacent behavior. The purpose of this quantitative correlational study was to evaluate the relationship between leaders' emotional intelligence resources and their ability to manage to prevent injuries and fatalities in the workplace. The research questions address key traits of emotional intelligence regarding emotional perceptions and control which are needed to make the leaders more effective at recognizing and responding to stress complacency related incidents. Specifically, this study includes a method of inquiry in the form of a survey designed to measure 140 leaders' emotional intelligence competencies in 3 Western Virginia food and beverage manufactories. Structural equation modeling was used to determine the multivariate relationships among leaders' skills and safety prevention. Leaders' emotional intelligence results indicated a negative effect on stress identification in either upper or middle leadership groups preventing them from exercising safe prevention error with their employees. Promoting leaders' emotional intelligence engagement may potentially contribute to social change helping the food and beverage organizations to protect their employees from getting hurt, promoting strong safety cultures, maintaining a positive impact on families and workers and thereby, increasing community resilience

Tragic, life-changing, and fatal incidents are a reality on large-scale, civil construction projects. Despite a decline following the enforcement of the 1971 Occupational Safety and Health Act, serious and fatal incidents on heavy construction projects remain higher than that of the active military and have not declined in any notable way in the past decade. Industrial-organizational literature suggested a lack of applied testing for the well-developed theory of authentic leadership (AL) to impact safety outcomes. This quasi-experiment combined the constructs of authentic leadership with safety climate perception as quantifiable measurement of potential safety outcomes in the workplace. The research question focused on whether AL would impact safety climate, thus, reducing injury and fatalities on the job. The researcher examined 1 of the 4 segments that comprised a $1 billion freeway improvement project. Perceptions of 108 field craft personnel were collected on a Likert-type instrument before and after their supervisors attended a brief AL workshop. Utilizing an ordinal scale, statistical significance was calculated pre- and postintervention by computing a Mann-Whitney U for independent samples. Significant improvement was found following the supervisor workshop. The reduction in incidents, when compared to the jobsite's history and the other 3 jobsite segments associated with the highway improvement project, suggests a potential for this framework to support positive social change, that is, to reduce the human cost and suffering associated with industrial accidents.

In Nigeria, displaced non-Muslim parents living in refugee camps face difficult decisions regarding the schooling of their teenage daughters, who are potential targets of Boko Haram terrorist activities. The purpose of this interpretative phenomenological analysis (IPA) was to qualitatively explore a deeper understanding of the lived experience of displaced non-Muslim parents in Nigeria concerning the schooling of their teenage daughters. Prospect theory provided a theoretical foundation for the study. The theory holds that decision-making is based on the perceived value of gains and losses under risk conditions, rather than solely the perceived final outcome of the risk. The research questions explored how the experience of terrorism affected parents' school-related decision-making, perceptions of the schooling environment and value of education, and risk-taking attitudes. Data were collected through semistructured interviews held with 12 participants from 2 refugee camps. The data were then analyzed using the steps recommended in IPA. Identified themes included parents' experience of trauma, their concern about the vulnerability of their school-going children, and their support for their daughters' education. The findings produced a deeper understanding of the psychological implications of terrorist activities for the families, as well as their perception of the educational needs of teenage girls. Recommendations include providing governmental and nongovernmental support for affected parents and teenage girls. Contributions to positive social change include developing advocacy and resources in support of displaced parents and schools for improving the educational status of teenage girls in Nigeria.

Current therapeutic treatment methods are ineffective in identifying at-risk sex offenders and reducing recidivism of known offenders, likely due to inadequate identification of specific traits of sex offenders. Previous research and prominent theories in the area of sex offender treatment, in terms of the biological foundation of substance abuse, behaviors of sex offenders, and the presence of aggression, helped to guide this research. Data about sex offenders were collected, as reported by mental health professionals who treat them and focused on three characteristics: maladaptive interpersonal behaviors, impulsivity, and antisocial behaviors, on which the research questions were formed to detect commonality. For this study, a phenomenological approach was chosen through a qualitative design and an 11-item open-ended questionnaire was developed with which 11 mental health professionals who treated sex offenders were interviewed. The audio was transcribed, the text was coded into the themes of the research questions, and the data was analyzed for commonality. The results indicate that all three traits in the research questions are common among sex offenders. The results of this research added to the framework of understanding of common behaviors among sex offenders and to positive social change by providing a clearer understanding of the three targeted behaviors. The information gathered from this qualitative research will guide larger-scale quantitative studies on the sex offender population, ultimately assisting sex offender treatment providers and forensic interviewers with more rapid identification of traits specific to sex offenders.

Obesity is a risk factor for chronic diseases among the ethnic minorities for adult immigrants in the United States. There have been many research studies conducted to examine the relationship between the predictors and obesity in minority groups in the United States, that relationship was unknown in Meskhetian Turk (Ahiska) immigrant populations. Guided by social ecological model and acculturation theory, this study examined the predictors of obesity in the Meskhetian Turk (Ahiska) immigrant population in the western United States. Data were collected from 109 participants using CDC's Behavioral Risk Factor Surveillance System, Stephenson Multigroup Acculturation Scale, and Perceived Stress Scale. Participants were recruited through flyers in a public setting and data were analyzed through SPSS using logistic regression and Spearman's correlation. The result of the study showed no statistical association between obesity and the predictors of age, gender, socio-economic status, physical activity, acculturation, and perceived stress. This study, however, showed a significant association between daily vegetable, fruit, and hamburger, cheeseburger or meat loaf consumption and obesity, and weekly vegetable consumption, monthly hamburger, cheeseburger or meat loaf consumption and moderate/morbid obesity. The study findings suggest that, through targeted community-based intervention and education programs, there is positive social change in the value of healthy lifestyle and the impact of the predictors of obesity, especially diet of Meskhetian Turk (Ahiska) immigrant population in the United States. Further investigation should focus into other causes of obesity using a larger sample size.