Matching Items (4)
Description
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.
ContributorsCrawford, Aaron (Author) / Levy, Roy (Thesis advisor) / Green, Samuel (Committee member) / Thompson, Marilyn (Committee member) / Arizona State University (Publisher)
Created2014
Description
The goal of this study was to explore the multidimensionality of gender typicality and its relation to preadolescents’ psychological adjustment. With a sample of 378 6th grade students (52% male; M age = 11.44, SD = .56; 48% White), I examined how four specific dimensions of gender typicality (behavior, appearance, activities, and peer preference) predict children’s global sense of typicality; whether children’s global sense of gender typicality, behavior, appearance, activities, and peer preference are differentially predictive of self-esteem, social preference, and relationship efficacy; and whether examining typicality of the other gender is important to add to own-gender typicality. Regression analyses indicated that all four specific typicality dimensions contributed to preadolescents’ overall sense of own- and other-gender typicality (except appearance for own-gender typicality). Generally, all domains of gender typicality were related to the four adjustment outcomes. Own-gender typicality related more strongly to self-esteem, social preference, and own-gender relationship efficacy than did other-gender typicality; other-gender typicality was more strongly related to other-gender relationship efficacy. Relations between typicality and adjustment were stronger for gender-based relationship efficacy than for self-esteem or social preference. Although some differences existed, relations between typicality and adjustment were generally similar across typicality domains. Results implicate the need to measure other-gender typicality in addition to own-gender typicality. Additional contributions and suggestions for future research are discussed.
ContributorsCook, Rachel (Author) / Martin, Carol L (Thesis advisor) / Updegraff, Kimberly A (Committee member) / Miller, Cindy F (Committee member) / Arizona State University (Publisher)
Created2015
Description
Legal cynicism, a concept that reflects how individuals feel about the law, can be linked to different theoretical traditions. However, inconsistencies in the way legal cynicism is operationalized abound. This study aimed to develop a more complete and psychometrically-sound measure of legal cynicism. Factor-analytic procedures were used on a sample of 502 undergraduate university students to create the scale and to test its directional accuracy. Using promax-rotated principal-axis factor analysis, a 4 dimensional factor structure emerged—legal apathy, legal corruption, legal discrimination, and low legal legitimacy. The 21-item scale has a high level of internal consistency (Cronbach’s α = .85; mean inter-item r = .58). Results from ordinary least squares regression models confirmed that the multidimensional legal cynicism scale is significantly correlated with criminal offending (β = .34, p < .001), net of low self-control and demographic characteristics.
ContributorsGifford, Faith (Author) / Reisig, Michael D. (Thesis advisor) / Wang, Xia (Committee member) / Wright, Kevin A. (Committee member) / Arizona State University (Publisher)
Created2015
Description
Rising inequality is a defining challenge in the 21st century and although the 2030 agenda for sustainable development is far from perfect, its commitment to tackling inequalities is praiseworthy. To this end, a deeper understanding of how social inequality affects sustainable development can help us rethink development policies and practices. Social inequality is multidimensional and in the last two decades, there has been an upsurge of research in this area. However, these research do not provide a comprehensive understanding of the nature and extent of inequality and its impact on the United Nations Sustainable Development Goals. In particular, they ignore important dimensions such as wealth and the environment in their analysis. In this dissertation, the discourse on how inequality has evolved is first explored and the analysis reveals that the inequality discourse has shifted from its early focus on the measurement of conditions, defined as the unequal distribution of income and/or material goods, towards a more comprehensive approach of measuring inequality of opportunities. Second, the dissertation examines the short run and long run relationship between social inequality and sustainable development. This is achieved by relying on panel data for 142 countries using the Coefficient of Human Inequality and the Sustainable Development Goals Index and the findings reveal that social inequality and sustainable development share a negative relationship which appears to be robust to the inclusion of controls and the country’s level of development. Finally, this dissertation examines the inequality situation in Guyana by relying on a survey of 403 households and in doing so it computes a measure of social inequality using the Atkinson index along with the dimensions of income, education, health, wealth and the environment. The dissertation finds that Guyana is experiencing a high level of social inequality and it is hindering the country’s progress on the sustainable development goals.
ContributorsArmstrong, Sydney (Author) / Chhetri, Netra NC (Thesis advisor) / Hernandez-Cortes, Danae DHC (Committee member) / Chhetri, Nalini NC (Committee member) / Arizona State University (Publisher)
Created2023