Theses and Dissertations from UMD

Permanent URI for this communityhttp://hdl.handle.net/1903/2

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 give thesis/dissertation in DRUM

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Subject: search.filters.subject.latent class analysis

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Adverse Childhood Experiences (ACEs) in Early Childhood and Their Associations with Middle Childhood Behavior Problems
    (2017) Schroeder, Allison; Mittal, Mona; Family Studies; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Experiences in early childhood lay the foundation for physical and psychological health and wellbeing throughout the life course. A large body of literature demonstrates a graded relationship between adverse childhood experiences (ACEs) and health and social outcomes. Children living in poverty are disproportionately likely to experience multiple adversities, placing them at risk for negative health and developmental outcomes and contributing to widening health disparities. Among the outcomes associated with ACEs are internalizing and externalizing behavior problems, which increase children’s risk of later depression and anxiety, substance use, criminality, low socioeconomic status, and chronic physical health problems. In spite of the substantial knowledge base that has developed around childhood adversity and its association with behavior problems, there are gaps in the literature that warrant further research. Firstly, few studies utilizing prospective longitudinal data have examined the role of timing and duration of exposure to adversities in early childhood, and their relationship with later behaviors. Secondly, researchers have only just begun exploring whether certain patterns or constellations of risk factors are common among different groups of children, and whether these patterns place certain groups at greater risk for behavior problems. A third gap relates to the role of father involvement by unmarried fathers and the potential for these fathers to promote more positive outcomes among children exposed to various levels of early adversity. The three studies in this dissertation analyze data from four waves of the Fragile Families and Child Wellbeing Study to document associations between ACEs experienced at ages 1, 3, and 5, and behavior problems at age 9. Life course theory provides an overarching framework for the dissertation. The first study examines the associations between the accumulation, timing, and duration of ACEs in the first five years of life and odds of behavior problems at age 9. The second study employs latent class analysis to identify patterns of risk exposure and their potential association with age 9 behaviors. The third study investigates whether early father involvement by fathers who were unmarried at the child’s birth moderates the association between early childhood adversity and age 9 behavior problems.
  • Thumbnail Image
    Item
    USING LATENT PROFILE MODELS AND UNSTRUCTURED GROWTH MIXTURE MODELS TO ASSESS THE NUMBER OF LATENT CLASSES IN GROWTH MIXTURE MODELING
    (2011) Liu, Min; Hancock, Gregory R.; Measurement, Statistics and Evaluation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Growth mixture modeling has gained much attention in applied and methodological social science research recently, but the selection of the number of latent classes for such models remains a challenging issue. This problem becomes more serious when one of the key assumptions of this model, proper model-specification is violated. The current simulation study compared the performance of a linear growth mixture model in determining the correct number of latent classes against two less parametrically restricted options, a latent profile model and an unstructured growth mixture model. A variety of conditions were examined, both for properly and improperly specified models. Results indicate that prior to the application of linear growth mixture model, the unstructured growth mixture model is a promising way to identify the correct number of unobserved groups underlying the data by using most model fit indices across all the conditions investigated in this study.
  • Thumbnail Image
    Item
    Group Involvement Experiences in College: Identifying a Thematic Taxonomy
    (2008-03-03) Dugan, John Patrick; Komives, Susan R; Counseling and Personnel Services; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    The purpose of this study was to explore whether latent phenomena could be identified to assist in the classification of students into subgroups based on their patterns of involvement across 21 types of co-curricular group experiences (e.g., cultural groups, student governance, club sports). Further analysis attempted to establish whether the emergent taxonomy of subgroups truly discriminated among students. This was accomplished through the use of data from the Multi-Institutional Study of Leadership, a national research program examining the influences of higher education on college student leadership development. The sample was comprised of 11,209 seniors from 50 institutions across the United States. The primary research question employed exploratory latent class analysis as a means to determine the number of latent factors underlying student patterns of involvement. A total of four latent factors were identified and students were classified into one of eight latent classes interpreted to reflect: Affinity Group Affiliates, Identity and Expression Leaders, Academic Careerists, Cultural Collegiates, Athletes, Social Recreators, Recreational Academics, and Social Collegiates. Findings from secondary research questions contributed to the validity of the taxonomy by demonstrating differential influences of latent class membership on a theoretically-derived measure of leadership. Significant relationships were also identified between latent classes and the demographic variables of race and gender. Results suggested a more complex composition of the category of collegiate identified in numerous taxonomies of college students (Astin, 1993a; Clark & Trow, 1966; Kuh, Hu & Vesper, 2000). Findings also served as a response to the numerous calls for research examining patterns of student involvement in co-curricular group experiences (Gellin, 2003; Foubert & Grainger, 2006; Hernandez, Hogan, Hathaway, & Lovell, 1999; Hoffman, 2002; Moore, Lovell, McGann, & Wyrick, 1998; Renn & Bilodeau, 2005a). Results have implications for both higher education research and professional practice. This includes the provision of new analytic and conceptual approaches for studying college student populations as well as college impact. Findings may also serve as a useful heuristic tool to assist student affairs professionals in their advising and mentoring of college students.