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

Subject: search.filters.subject.multilevel modeling

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Reading Analyses with Chilean Children
    (2021) Cubillos Guzman, Montserrat; Turner, Jennifer; Galindo, Claudia; Education Policy, and Leadership; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Chilean data show that a large reading-proficiency gap exists between students with high and low socioeconomic status (SES), that most children do not see themselves as readers, and that half of adolescents read below grade level (Agencia de Calidad de la Educación, 2019; Consejo Nacional de la Cultura y las Artes, 2014). To understand the reasons behind these phenomena, I conducted three complementary studies on reading comprehension, motivation, and literacy-related home practices with over 800,000 Chilean students, using nation-wide secondary data analysis.In the first study, I examined the association between the frequency of early literacy parent-children interactions (e.g., reading together, reading labels and signs, singing songs, etc.) before they entered first grade and students’ reading scores in fourth grade, while accounting for their second-grade proficiency. I observed that parents frequently engaged in literacy interactions with their children, that those interactions significantly predicted students’ later reading proficiency, and that the effect was steeper for families with high SES than for those with low SES. In the second study, I explored the association between parents’ reading motivation and frequency and their children’s. I examined data of students from sixth, eight, and tenth grade. I found that adolescents were more likely to be motivated and frequent readers if their parents were also keen readers. I also found that SES was a powerful predictor of the likelihood of being a keen reader, and that the effect of having a keen-reading parent was more positively pronounced for adolescents with low SES than for those with high SES. In the third study, I explored whether tenth graders’ reading motivation and frequency was associated to their reading scores. I observed that a large percentage of students who were proficient readers in fourth grade failed to achieve proficiency in tenth grade and that the odds of achieving proficiency in tenth grade increased when students were motivated and frequent readers. Furthermore, students’ odds of being proficient readers increased when their classmates reported high levels of reading motivation and frequency of reading. I discuss the implications of this and my other two studies.
  • Thumbnail Image
    Item
    Multilevel Regression Discontinuity Models with Latent Variables
    (2020) Morell, Monica; Yang, Ji Seung; Liu, Yang; Measurement, Statistics and Evaluation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Regression discontinuity (RD) designs allow estimating a local average treatment effect (LATE) when assignment of an individual to treatment is determined by their location on a running variable in relation to a cutoff value. The design is especially useful in education settings, where ethical concerns can forestall the use of randomization. Applications of RD in education research typically share two characteristics, which can make the use of the conventional RD model inappropriate: 1) The use of latent constructs, and 2) The hierarchical structure of the data. The running variables often used in education research represent latent constructs (e.g., math ability), which are measured by observed indicators such as categorical item responses. While the use of a latent variable model to account for the relationships among item responses and the latent construct is the preferred approach, conventional RD analyses continue to use observed scores, which can result in invalid or less informative conclusions. The current study proposes a multilevel latent RD model which accounts for the prevalence of clustered data and latent constructs in education research, allows for the generalizability of the LATE to individuals further from the cutoff, and allows researchers to quantify the heterogeneity in the treatment effect due to measurement error in the observed running variable. Models are derived for two of the most commonly used multilevel RD designs. Due to the complex and high-dimensional nature of the proposed models, they are estimated in one stage using full-information likelihood via the Metropolis-Hastings Robbins-Monro algorithm. The results of two simulation studies, under varying sample size and test length conditions, indicate the models perform well when using the full sample with at least moderate-length assessments. A proposed model is used to examine the effects of receiving an English language learner designation on science achievement using the Early Childhood Longitudinal Study. Implications of the results of these studies and future directions for the research are discussed.
  • Thumbnail Image
    Item
    A MULTILEVEL ANALYSIS OF CONTEXT EFFECTS ON ADOLESCENT CIVIC ENGAGEMENT: THE ROLE OF FAMILY, PEERS, SCHOOL, AND NEIGHBORHOOD
    (2009) Wilkenfeld, Britt Skeens; Torney-Purta, Judith; Human Development; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    The relations between multiple contexts of influence and adolescents' civic engagement were examined in order to facilitate understanding of how adolescents are being prepared for citizenship. This study extends previous research by simultaneously examining the family, peer, school, and neighborhood contexts, including how contexts are interrelated in their influence, and by employing multilevel regression techniques. The purpose of the study was to understand how contexts interact to produce positive outcomes for adolescents, especially those deemed at risk for poor civic outcomes. Utilizing data from the 1999 Civic Education Study and the 2000 U.S. Census, I examined a nationally representative sample of 2,729 14-year-olds from 119 schools in the United States. Access to the zip-codes for each school that participated in the study enabled the connection between neighborhood characteristics and schools and students within schools. Given the multifaceted nature of civic engagement, the current study considered context effects on four different aspects of civic engagement: civic knowledge, support for the rights of ethnic minorities, anticipated voting behavior, and anticipated community participation. Predictors pertain to adolescents' demographic characteristics, political discourse with parents and peers, civic experiences in school, and the demographic composition of the neighborhood. Political discourse with parents was positively related to civic knowledge, attitudes, and anticipated behavior, indicating the consistency with which socialization occurs in the home. Across the contexts examined, student measures of civic experiences in school (or civic learning opportunities) had the most consistently positive relationships with students' civic outcomes. Civic experiences in school include student confidence in the effectiveness of school participation, perception of a classroom climate that is open for discussion, and learning about ideal civic practices. Interactions between the school and neighborhood contexts indicate that higher levels of civic learning opportunities particularly make a difference for students attending schools in impoverished neighborhoods, sometimes substantially improving their civic outcomes. Schools, although implicated in the existence of a civic engagement gap, have the potential to narrow the gaps. Civic experiences in schools contribute to the preparation of youth for active citizenship and full access to these experiences reduces civic engagement gaps between students of different demographic groups.