UMD Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/3
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
5 results
Search Results
Item A Mean-Parameterized Conway–Maxwell–Poisson Multilevel Item Response Theory Model for Multivariate Count Response Data(2024) Strazzeri, Marian Mullin; Yang, Ji Seung; Measurement, Statistics and Evaluation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Multivariate count data arise frequently in the process of measuring a latent construct in human development, psychology, medicine, education, and the social sciences. Some examples include the number of different types of mistakes a student makes when reading a passage of text, or the number of nausea, vomiting, diarrhea, and/or dysphagia episodes a patient experiences in a given day. These response data are often sampled from multiple sources and/or in multiple stages, yielding a multilevel data structure with lower level sampling units (e.g., individuals, such as students or patients) nested within higher level sampling units or clusters (e.g., schools, clinical trial sites, studies). Motivated by real data, a new Item Response Theory (IRT) model is developed for the integrative analysis of multivariate count data. The proposed mean-parameterized Conway--Maxwell--Poisson Multilevel IRT (CMPmu-MLIRT) model differs from currently available models in its ability to yield sound inferences when applied to multilevel, multivariate count data, where exposure (the length of time, space, or number of trials over which events are recorded) may vary across individuals, and items may provide different amounts of information about an individual’s level of the latent construct being measured (e.g., level of expressive language development, math ability, disease severity). Estimation feasibility is demonstrated through a Monte Carlo simulation study evaluating parameter recovery across various salient conditions. Mean parameter estimates are shown to be well aligned with true parameter values when a sufficient number of items (e.g., 10) are used, while recovery of dispersion parameters may be challenging when as few as 5 items are used. In a second Monte Carlo simulation study, to demonstrate the need for the proposed CMPmu-MLIRT model over currently available alternatives, the impact of CMPmu-MLIRT model misspecification is evaluated with respect to model parameter estimates and corresponding standard errors. Treating an exposure that varies across individuals as though it were fixed is shown to notably overestimate item intercept and slope estimates, and, when substantial variability in the latent construct exists among clusters, underestimate said variance. Misspecifying the number of levels (i.e., fitting a single-level model to multilevel data) is shown to overestimate item slopes---especially when substantial variability in the latent construct exists among clusters---as well as compound the overestimation of item slopes when a varying exposure is also misspecified as being fixed. Misspecifying the conditional item response distributions as Poisson for underdispersed items and negative binomial for overdispersed items is shown to bias estimates of between-cluster variability in the latent construct. Lastly, the applicability of the proposed CMPmu-MLIRT model to empirical data was demonstrated in the integrative data analysis of oral language samples.Item Estimating the Prevalence and Timing of Events Along the Pathway to Identification of Autism in the US 2016–2018(2021) Hanley, Allison; Nguyen, Quyhn; Public and Community Health; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The prevalence of autism spectrum disorder (ASD) has risen rapidly in the past decade. Estimates on factors associated with developmental screening and the timing of events along the diagnostic pathway can inform early identification efforts. This dissertation uses cross-sectional data from the 2016–2018 National Survey of Children’s Health to achieve 3 aims: 1) evaluate individual- and state-level sources of variance between states in developmental screening rates via multilevel models, 2) evaluate characteristics associated with the ages at which children with ASD are first diagnosed, receive an intervention plan, and begin intervention, and 3) evaluate differences in lengths of time between these events by cohort. Aim 1: The national rate of developmental screening for children ages 9 months to 5 years is 34.4% (95% Confidence Interval (CI), [34.3, 34.4]). Rates varied between states by 38%. Individual-level factors explained 6% of the variance, while income inequality and a state’s choice to track developmental screening did not explain any variance between states. Aim 2: Linear regression models adjusted for individual and household characteristics showed that compared to children aged 3–5 years at the time of the survey, children 6–11 were 18 months older at first services (? =1.49, 95% CI, [1.18, 1.81] and children aged 12–17 were 38 months older at first ASD diagnosis (? =3.16, 95% CI, [2.72, 3.60]. Aim 3: Analyses using identical models showed that compared to children aged 3–5 at the time of the survey, the interval between first plan and first services was 4 months longer for children 6–11 (? =0.34, 95% CI, [0.07, 0.61]; and 8 months longer between first ASD diagnosis and first services for children aged 12–17 (? =0.67, 95% CI, [0.28, 1.06]. Today’s children with autism receive their first diagnosis, intervention plans, and developmental services at younger ages than in the past and are moving between events with less delay compared to older children. However, the low rate of developmental screening nationwide represents missed opportunities for even earlier identification. Research is needed to identify the macro-level factors that explain the variance between states on developmental screening rates.Item Police Legitimacy in Sub-Saharan Africa(2016) Behlendorf, Brandon Paul; LaFree, Gary; Criminology and Criminal Justice; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Is fairness in process and outcome a generalizable driver of police legitimacy? In many industrialized nations, studies have demonstrated that police legitimacy is largely a function of whether citizens perceive treatment as normatively fair and respectful. Questions remain whether this model holds in less-industrialized contexts, where corruption and security challenges favor instrumental preferences for effective crime control and prevention. Support for and against the normative model of legitimacy has been found in less-industrialized countries, yet few have simultaneously compared these models across multiple industrializing countries. Using a multilevel framework and data from respondents in 27 countries in sub-Saharan Africa (n~43,000), I find evidence for the presence of both instrumental and normative influences in shaping the perceptions of police legitimacy. More importantly, the internal consistency of legitimacy (defined as obligation to obey, moral alignment, and perceived legality of the police) varies considerably from country to country, suggesting that relationships between legality, morality, and obligation operate differently across contexts. Results are robust to a number of different modeling assumptions and alternative explanations. Overall, the results indicate that both fairness and effectiveness matter, not in all places, and in some cases contrary to theoretical expectations.Item Transferring social capital from individual to team: An examination of moderators and relationships to innovative performance(2012) Edinger, Suzanne; Tesluk, Paul E; Business and Management: Management & Organization; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this dissertation, I explore the relationships between individual social capital, team social capital, and team innovative performance. The association between personal and group social capital is underexplored (Burt, 2000; Kilduff & Krackhardt, 2008), and is important to investigate so that we may improve our knowledge of how social capital transfers from individuals to their teams in ways that promote team innovation. I hope to contribute to the literature on social capital in teams in three important ways. Within team-based settings with high innovation requirements, I first propose that the structural bridging social capital (i.e., ties outside the team) of team members is an important predictor of the team's structural bridging social capital. Second, transferring social capital from the individual to team level, I suggest that a team member's sharing of his/her bridging social capital resources is influenced by relational, cognitive, and task components, including group identification, dyadic trust, team member exchange, and shared vision. Finally, I investigate the role of transactive memory systems and bonding social capital (i.e., ties inside the team) in explaining the relationship between team structural bridging social capital and team innovative performance. Study participants were 263 members of 38 project teams in the merchandising displays division of a large paperboard and packaging manufacturer in the United States. I find that individual bridging social capital predicts team structural bridging social capital. Additionally, psychological identification with team, psychological identification with organization, team member exchange, and shared vision moderate the relationship between individual and team structural social capital. I conclude by discussing the implications of these findings for social capital and team innovative performance theory and practice.Item Teachers' Ratings of Relationships with Students: Links to Student and Teacher Characteristics(2012) Buhl, Sara J.; Rosenfield, Sylvia; Counseling and Personnel Services; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This exploratory study examined the associations between teacher-student relationship ratings and characteristics of students and teachers. A sample of fifth grade teachers (N = 115) and their students (N = 2070) were studied. Hierarchical linear modeling was employed to explore the associations between variables while taking both individual characteristics and classroom context into account. An investigation of within-teacher variation indicated that males, Asian students, Hispanic students, FARM eligible students, and students with high prior internalizing scores generally received lower closeness scores. A between-teacher (level-2) model was created to gain a better understanding of the influence of classroom context on teacher reports of closeness with their students. Classroom context was found to play a significant role in relationship ratings for students in general and also for subpopulations of students (i.e., male, high prior externalizing, or high prior internalizing). Teacher self efficacy was positively associated with relationship closeness. Longitudinal data were used to explore the association between the ratings that teachers had provided during previous years (with prior students) and ratings of closeness with their current students. Results indicated that teacher ratings of their previous students during prior years were a significant positive predictor of how their current relationships were rated. Implications, limitations, and directions for future research are discussed.