11 Matching Results

Search Results

Advanced search parameters have been applied.

Time Series Data Analysis of Single Subject Experimental Designs Using Bayesian Estimation

Description: This study presents a set of data analysis approaches for single subject designs (SSDs). The primary purpose is to establish a series of statistical models to supplement visual analysis in single subject research using Bayesian estimation. Linear modeling approach has been used to study level and trend changes. I propose an alternate approach that treats the phase change-point between the baseline and intervention conditions as an unknown parameter. Similar to some existing approaches, the models take into account changes in slopes and intercepts in the presence of serial dependency. The Bayesian procedure used to estimate the parameters and analyze the data is described. Researchers use a variety of statistical analysis methods to analyze different single subject research designs. This dissertation presents a series of statistical models to model data from various conditions: the baseline phase, A-B design, A-B-A-B design, multiple baseline design, alternating treatments design, and changing criterion design. The change-point evaluation method can provide additional confirmation of causal effect of the treatment on target behavior. Software codes are provided as supplemental materials in the appendices. The applicability for the analyses is demonstrated using five examples from the SSD literature.
Date: August 2015
Creator: Aerts, Xing Qin
Partner: UNT Libraries

Comparing Three Effect Sizes for Latent Class Analysis

Description: Traditional latent class analysis (LCA) considers entropy R2 as the only measure of effect size. However, entropy may not always be reliable, a low boundary is not agreed upon, and good separation is limited to values of greater than .80. As applications of LCA grow in popularity, it is imperative to use additional sources to quantify LCA classification accuracy. Greater classification accuracy helps to ensure that the profile of the latent classes reflect the profile of the true underlying subgroups. This Monte Carlo study compared the quantification of classification accuracy and confidence intervals of three effect sizes, entropy R2, I-index, and Cohen’s d. Study conditions included total sample size, number of dichotomous indicators, latent class membership probabilities (γ), conditional item-response probabilities (ρ), variance ratio, sample size ratio, and distribution types for a 2-class model. Overall, entropy R2 and I-index showed the best accuracy and standard error, along with the smallest confidence interval widths. Results showed that I-index only performed well for a few cases.
Date: December 2015
Creator: Granado, Elvalicia A.
Partner: UNT Libraries

A Performance Evaluation of Confidence Intervals for Ordinal Coefficient Alpha

Description: Ordinal coefficient alpha is a newly derived non-parametric reliability estimate. As with any point estimate, ordinal coefficient alpha is merely an estimate of a population parameter and tends to vary from sample to sample. Researchers report the confidence interval to provide readers with the amount of precision obtained. Several methods with differing computational approaches exist for confidence interval estimation for alpha, including the Fisher, Feldt, Bonner, and Hakstian and Whalen (HW) techniques. Overall, coverage rates for the various methods were unacceptably low with the Fisher method as the highest performer at 62%. Because of the poor performance across all four confidence interval methods, a need exists to develop a method which works well for ordinal coefficient alpha.
Date: May 2015
Creator: Turner, Heather Jean
Partner: UNT Libraries

A Structural and Psychometric Evaluation of a Situational Judgment Test: The Workplace Skills Survey

Description: Some basic but desirable employability skills are antecedents of job performance. The Workplace Skills Survey (WSS) is a 48-item situational judgment test (SJT) used to assess non-technical workplace skills for both entry-level and experienced workers. Unfortunately, the psychometric evidence for use of its scores is far from adequate. The purpose of current study was two-fold: (a) to examine the proposed structure of WSS scores using confirmatory factor analysis (CFA), and (b) to explore the WSS item functioning and performance using item response theory (IRT). A sample of 1,018 Jamaican unattached youth completed the WSS instrument as part of a longitudinal study on the efficacy of a youth development program in Jamaica. Three CFA models were tested for the construct validity of WSS scores. Parameter estimations of item difficulty, item discrimination, and examinee’s proficiency estimations were obtained with item response theory (IRT) and plotted in item characteristics curves (ICCs) and item information curves (IICs). Results showed that the WSS performed quite well as a whole and provided precise measurement especially for respondents at latent trait levels of -0.5 and +1.5. However, some modifications of some items were recommended. CFA analyses showed supportive evidence of the one-factor construct model, while the six-factor model and higher-order model were not achieved. Several directions for future research are suggested.
Date: August 2014
Creator: Wei, Min
Partner: UNT Libraries

Reliability Generalization: a Systematic Review and Evaluation of Meta-analytic Methodology and Reporting Practice

Description: Reliability generalization (RG) is a method for meta-analysis of reliability coefficients to estimate average score reliability across studies, determine variation in reliability, and identify study-level moderator variables influencing score reliability. A total of 107 peer-reviewed RG studies published from 1998 to 2013 were systematically reviewed to characterize the meta-analytic methods employed and to evaluate quality of reporting practice against standards for transparency in meta-analysis reporting. Most commonly, RG studies meta-analyzed alpha coefficients, which were synthesized using an unweighted, fixed-effects model applied to untransformed coefficients. Moderator analyses most frequently included multiple regression and bivariate correlations employing a fixed-effects model on untransformed, unweighted coefficients. Based on a unit-weighted scoring system, mean reporting quality for RG studies was statistically less than that for a comparison study of 198 meta-analyses in the organizational sciences across 42 indicators; however, means were not statistically significantly different between the two studies when evaluating reporting quality on 18 indicators deemed essential to ethical reporting practice in meta-analyses. Since its inception a wide variety of statistical methods have been applied to RG, and meta-analysis of reliability coefficients has extended to fields outside of psychological measurement, such as medicine and business. A set of guidelines for conducting and reporting RG studies is provided.
Date: December 2015
Creator: Holland, David F.
Partner: UNT Libraries

Examining the Relationship Between Persistence in Attendance in an Afterschool Program and an Early Warning Index for Dropout

Description: School districts constantly struggle to find solutions to address the high school dropout problem. Literature supports the need to identify and intervene with these students earlier and in more systemic ways. The purpose of this study was to conduct a longitudinal examination of the relationship between sustained afterschool participation and the host district’s early warning index (EWI) associated with school dropout. Data included 65,341 students participating in an urban school district’s after school program from school years 2000-2001 through 2011-2012. The district serves more than 80,000 students annually. Data represented students in Pre-Kindergarten through Grade 12, and length of participation ranged from 1 through 12 years. Results indicated that student risk increased over time and that persistent participation in afterschool programming had a significant relationship with student individual growth trajectories. Slower growth rates, as evidenced through successive models, supported students being positively impacted by program participation. Additionally, participation was more meaningful if students persisted, as noted in the lower EWI rates, as compared to students who attended less consistently.
Date: May 2014
Creator: King, Teresa C.
Partner: UNT Libraries

Perceptions of Family Vacation and Family Cohesion and the Moderating Effects of Parenting Style

Description: Family cohesion, or emotional bonding, is important to family functioning. Shared activities such as family vacations offer opportunities for strengthening the family unit which can improve cohesion. Additionally, parenting style has direct influence on the family unit and family cohesion. This study’s purpose was to assess to what extent the perception of the family vacation experience predicted the perception of family cohesion and whether that relationship was moderated by parenting style. An online survey was conducted, resulting in 97 adult participants responding to items regarding their last family vacation, family cohesion, and parenting style. Using hierarchical multiple regression, a medium effect size was found for the predictive ability of a participant’s perception of their last family vacation on family cohesion. Findings also indicated a negative correlation between an authoritarian parenting style and perception of family cohesion, but a positive relationship between the interaction of family vacation experience and authoritarian parenting to family cohesion. Stronger predictive abilities were found for those with children in the 3-11 age group. Results may encourage parent and family educators to use family vacation as a tool in assisting families with the processes of building strong and cohesive families.
Date: May 2014
Creator: Kruenegel-Farr, Debbie S.
Partner: UNT Libraries

Pathways From ADHD Symptoms to Obesity in a College Population

Description: Attention deficit hyperactivity disorder (ADHD) is more recently being recognized as a lifetime disorder that continues to affect individuals into their adult lives. Recent research studies have found connections between ADHD and overweight/obesity. The current study was designed to further explore these relationships and better understand the connections between these two constructs among 340 college students. It was hypothesized that the ADHD symptoms (i.e., inattention and impulsivity) would positively predict depressive symptoms, which in turn would predict emotional/binge eating and lead to overweight/obesity. Additionally, it was hypothesized that impulsivity would predict substance use, which would predict emotional/binge eating and also predict overweight/obesity. The model was tested and exhibited excellent fit. ADHD positively predicted depressive symptoms, which in turn positively predicted emotional/binge eating and led to overweight/obesity. Further, ADHD symptoms also positively predicted substance use, which in turn predicted emotional/binge eating and led to overweight/obesity. All paths were statistically significant and findings suggest there are at least two paths that connect ADHD symptoms and overweight/obesity in adults. The current results are of importance to practicing clinicians because they provide increased clarity and depth regarding the connections and relationship between symptoms of ADHD and overweight/obesity.
Date: August 2014
Creator: Marcom, Leslee Johnson
Partner: UNT Libraries

Construct Validation of the Social-Emotional Character Development Scale in Belize: Measurement Invariance Through Exploratory Structural Equation Modeling

Description: Social-emotional learning (SEL) measures assessing social-emotional learning and character development across a broad array of constructs have been developed but lack construct validity. Determining the efficacy of educational interventions requires structurally valid measures which are generalizable across settings, gender, and time. Utilizing recent factor analytic methods, the present study extends validity literature for SEL measures by investigating the structural validity and generalizability of the Social-Emotional and Character Development Scale (SECDS) with a large sample of children from schools in Belize (n = 1877, ages 8 to13). The SECDS exhibited structural and generalizability evidence of construct validity when examined under exploratory structural equation modeling (ESEM). While a higher order confirmatory factor structure with six secondary factors provided acceptable fit, the ESEM six-factor structure provided both substantive and methodological advantages. The ESEM structural model situates the SECDS into the larger body of SEL literature while also exhibiting generalizability evidence over both gender and time.
Date: August 2014
Creator: Hinerman, Krystal M.
Partner: UNT Libraries

Criterion Validity of Common Career Interest Inventories: Relative Efficacy with High School Seniors

Description: Professional school counselors frequently use career interest inventories as part of a comprehensive guidance program to help students create a post-secondary school plan. The present study evaluates the validity of three commonly used interest inventories, the Myers-Briggs Type Indicator, Self-Directed Search, and Strong Interest Inventory on field of study choice for graduating high school seniors (N = 616) from a large, suburban high school in Texas. Students identified their intended postsecondary field of study category, were randomly assigned using stratification to three groups, and each group completed a different inventory. Group membership was evaluated to establish covariate balance on a wide variety of indicators. Data from each group was evaluated to determine the extent to which the inventory predicted the chosen field of study, as well as Other and Undeclared categories using logistic regression models. None of the inventory models suggest that the inventory accurately predicts Other or Undeclared outcomes. For students selecting intended postsecondary fields of study, the Self Directed Search predicts such outcomes better than other measures. Professional school and career counselors should consider the SDS in addition to narrative counseling strategies to add greater precision with career decision making among clients and students.
Date: August 2014
Creator: Martin, Summer M.G.
Partner: UNT Libraries

A Comparative Analysis of State Funds on Student Achievement of Economically Disadvantaged Elementary Schools in Independent School Districts and Charter Schools in the State of Texas

Description: The purpose of this study was to evaluate the relationship between the instructional outcomes in the independent school districts and charter schools in relation to the expenditure of public funds for instruction and total operating expenditures from the general fund. The study considered Texas elementary charter schools and independent school districts, whose school populations were identified as having greater than or equal to 50% of economically disadvantaged students, according to the Texas Academic Excellence Indicator System (AEIS). The study made use of multiple regression and was an ex post facto cross-sectional analysis utilizing production function theory. The study’s outcomes reported the difference in student achievement between elementary schools in independent public school districts and charter schools were small to negligible for math and reading achievement. The study also reported, there is no statistically significant difference in per pupil expenditure of public funds between elementary schools in independent public school districts and charter schools. Furthermore, there is no statistically significant relationship between student achievement and per pupil expenditure of public funds on elementary schools in independent public school districts and charter schools.
Date: May 2015
Creator: Applewhite, Gary
Partner: UNT Libraries