Search

The application of diagnostic classification models (DCMs) in the field of educational measurement is getting more attention in recent years. To make a valid inference from the model, it is important to ensure that the model fits the data. The purpose of the present study was to investigate the performance of the limited information goodness-of-fit statistic Mord in the polytomous response DCMs with the presence of hierarchical attribute structures. The first simulation study investigated the empirical Type I error rates of the Mord statistic under the null hypothesis when the model and data were perfectly fitted. The second simulation study explored the empirical rejection rate of M[subscript ord] under different types of misspecifications: model misspecification, attribute hierarchy misspecification, and Q-matrix misspecification. The impact of test length, item quality, attribute structure, marginal/conditional probability of the mastery of attributes, and the number of response categories were investigated. The results indicated that the M[subscript ord] statistic demonstrated well-calibrated Type I error rates under the null conditions with different types of hierarchical attribute structures. When there were model-data misfits, the M[subscript ord] statistic showed high empirical rejection rates in detecting the misspecified sDINA and sDINO but didn't show enough power to detect the sC-RUM. The M[subscript ord] also exhibited high empirical rejection rates when the generating attribute structure was non-strict hierarchical, but the fitted structure was strict hierarchical. Besides, it was sensitive when the sequence of parent and child attributes was reversed. However, the M[subscript ord] statistic couldn't detect the omission of hierarchical attribute connections. When there were Q-matrix misspecifications, the M[subscript ord] statistic showed extremely high empirical rejection rates in the condition of Q-matrix under-specification but was not sensitive to the Q-matrix over-specification. The higher proportion of Q-matrix misspecification led to higher Mord rejection rates. The item quality exhibited a huge influence on the performance of the M[subscript ord] statistic. The M[subscript ord] statistic demonstrated higher empirical rejection rates with higher item quality, longer test length, fewer item response categories, and lower marginal/conditional probability of the mastery of attributes. The types of attribute structure also demonstrated slight influences on the rejection rates of the M[subscript ord] statistics under some circumstances. The performance of the RMSEA[subscript ord] and SRMSR were explored in the present study to assess the degree of misfit and absolute model fit. The results indicated that the frequently used cut-off value of 0.05 was not appropriate in the framework of polytomous response DCMs. The magnitude of RMSEA[subscript ord] and SRMSR values varied in different situations. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

This quantitative research study analyzed archival data to determine if there was a significant difference in promotion rates from third to fourth grade between students in foster care who received one-to-one tutoring and those students in foster care who did not receive one-to-one tutoring over two school years. This study also analyzed student records to determine if there were significant differences in the promotion rates from third to fourth grade between students who received one-to-one tutoring for one to six months and students who received tutoring for seven months or more. The sample consisted of 167 third grade students in foster care in the state of Georgia. A descriptive comparative research design was used to gather and analyze data to find the difference in promotion rates among these three groups. A Chi-Square Goodness-of-Fit test was used to determine if there was a significant difference in promotion rates between third-grade foster care youth who received tutoring and those who did not; to determine if there was a significant difference in promotion rates between third-grade foster care youth who received tutoring for up to six months and third grade foster care youth who did not receive tutoring; and to determine if there was a significant difference in promotion rates between third-grade foster care youth who received tutoring for up to six months and third-grade foster care youth who received tutoring for seven months or more. Practical implications for this study suggest that tutoring as an intervention is effective at increasing the promotion rates of third grade youth in foster care, but that there is not significant difference in promotion rates for those students who did not receive tutoring. If the child does receive tutoring, the results indicate that tutoring for more than six months is more beneficial. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

When researchers fit statistical models to multiply imputed datasets, they have to fit the model separately for each imputed dataset. Since there are multiple datasets, there are always multiple sets of model results. It is possible for some of these sets of results not to converge while some do converge. This study examined occurrence of such a problem--partial convergence problem and inspected four outcomes of partially convergent models: proportion of convergence, percent parameter bias, root mean square error, and coverage rate of the true population parameter in the confidence interval of the parameter estimates. In this Monte Carlo simulation study complete data with standard normal distribution were simulated based on a single CFA model with 3 factors each with 3 indicators. True factor loadings for each factor varied as 0.4, 0.6, and 0.8. A single factor covariance of 0.4 was set as the true population parameter. In addition to variation of the factor loadings, sample size levels varied as 60, 80, 100, 150, 200, 300, and 400 and rate of missingness varied as 5%, 10%, 25%, and 50%. Partial convergence problem was not observed for sample size levels of 300 and 400. Thus, these conditions were not examined any further. It was examined that partial convergence problem was more likely to occur when the sample size was small and rate of missingness was high. It was observed that factor loading estimations were unbiased, however, there were two cells (sample of 60 with 25% missingness and sample size of 150 with 50% missingness) where factor covariance estimations were biased. Even though, overall for most cells parameter estimates were unbiased, root mean square errors were high across sample sizes for the 50% missingness condition which indicates that the parameter estimates for the 50% missingness were inconsistent across replications. Almost for all conditions, confidence intervals of the parameter estimates did not contain the true population parameter at acceptable rate--90% or higher. A different solution to the partial convergence problem was examined in this study. For the sets of results that did not converge, additional imputations were conducted to examine whether any of the outcomes would be improved. The only improvement was observed in the proportion of convergence outcome, indicating, that re-imputation may result in fully convergence of models, however, this will have no effect on percent parameter bias, root mean square error or the coverage rate of the confidence intervals. Recommendations for researchers who deal with the partial convergence problem are provided. Limitations of the study are acknowledged and suggestions for future research are given. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Researchers have assumed that social cognitive factors play significant roles in the career development of transition youth and young adults with disabilities and those without disabilities. However, research on the influence of the career decision-making process as a primary causal agent in one's psychosocial outcomes such as perceived level of quality of life remains limited. Therefore, the purpose of the present study was twofold: (a) to evaluate the general compatibility (i.e., goodness of fit) of the hypothesized model with the data; and (b) to determine the effect of career decision self-efficacy, career decision-making outcome expectations, goals, and perceived contextual supports on the quality of life of college students with disabilities. Serving as a theoretical framework for the current study was Social Cognitive Career Theory (SCCT). This theory provides a lens with which to explore the predictive utility of social cognitive variables related to college students with disabilities by focusing on the strength of an individual's beliefs, cognitive, and environmental systems. Participating in the study were 386 college students with disabilities currently enrolled in 2-year and 4-year private/public colleges and universities in a Midwestern state. They completed demographic information, career decision self-efficacy, career decision-making outcome expectations, goals, perceived contextual supports, and quality of life measures. Based on an online, quantitative descriptive survey design, a series of statistical analyses including exploratory factor analysis, confirmatory factor analysis, descriptive statistics, Pearson correlations, and structural equation modeling was used to interpret results, answer the research question and examine the hypothesis. Results showed that the structural model of career development and the quality of life of college students with disabilities adequately fit the data. They provide empirical support for the significant direct and indirect effects among the social cognitive variables and quality of life. The findings suggest that the obtained model predicts the quality of life of college students with disabilities from a combination of career decision self-efficacy, career decision-making outcome expectations, goals, and perceived contextual supports. Data generated from the present study can be used to inform current practitioners in the career development and vocational rehabilitation fields as well as college students with disabilities and their families. The findings were discussed in light of process aspects of career development and overall quality of life and strengths and limitations of the study were provided. Implications for practice and future research are also discussed. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

This dissertation examines the reciprocal relationship between text literacy and music literacy through an experimental design. Music teachers and English Language Arts (ELA) teachers often address similar components of literacy, including fluency, comprehension, and symbolic interpretation. The theory of cognitive structuralism maintains that through derivative and correlative subsumption, material that is learned in one context is strengthened when applied in a disparate context. Therefore, ELA and music teachers who work in isolation are missing an opportunity to teach parallel literacy concepts for the common advantage of teachers and students. This study seeks to explain how students enrolled in conventional and literacy-enriched band environments perform better than non-band students on text literacy tests. It also asks if conventional band students differ from literacy-enriched band students on text and musical literacy tests. Fourth-grade students were randomly assigned to one of three groups: a control group (n = 11), a conventionally taught beginning band group (n = 11), and a literacy-enriched beginning band group (n = 10). The experimental treatment included 14 small group band lessons and 14 full band rehearsals. Groups were then compared for textual literacy growth using the NWEA Measures of Academic Performance (MAP) and musical growth using the Watkins Farnum Performance Scale (WFPS). ANCOVA planned contrasts showed that literacy-enriched students significantly outperformed conventional band students and control students on the MAP literature reading subtest. The research design allowed for the defense of literacy-enriched band instruction as a generalizable cause of higher literacy scores. Additional comparisons between the control group and the two experimental groups revealed no statistically significant differences between the group means on the overall reading scores or the remaining reading subtest scores. The lack of significance suggested that the statistical model was a poor fit for the data. Furthermore, a small sample size and large unexplained variance contributed to a lack of statistical power. Therefore, the application of the cognitive structuralist theory on the remaining MAP reading tests remained inconclusive. The conventional and literacy-enriched band groups were also compared against each other on text and music literacy growth. There were no statistically significant differences between the conventional group and literacy-enriched group on the MAP or on the WFPS. This suggested that literacy-enriched instruction in band could benefit a student's textual literacy skills without compromising musical performance goals. It also suggested that more study is needed to determine the extent to which the explicit instruction of ELA reading skills in band may benefit musical ability. The overall findings implied that literacy-enriched band instruction caused higher textual literacy scores, and the results may be generalized to similar circumstances. Suggestions for practice included increased collaboration among teachers, enhanced teacher pre-service and in-service opportunities, additional use of student-centered progressive instructional strategies, and the careful reconsideration of eliminating or reducing the availability of band to students. Future research would benefit from the quantitative and qualitative models proposed herein. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The purpose of this study is to further enhance the existing reliability and validity evidence related to the School Implementation Scale (SIS) and its use for evaluating the implementation of different integrated academic and behavior tiered Response-To-Intervention (RTI) models. Previous methodology conducted for validation of the instrument has been expanded to examine the factor structure of the measurement instrument and the relationship between those factors across two overall state-implemented educational initiatives and across two different types of integrated academic and behavior multi-tiered systems of support within and between two states. The exploratory and confirmatory factor analyses that have been conducted in both SPSS and Mplus on the five datasets (Midwestern Collaborative Work, Western Effective Behavioral and Instructional Support Systems, Midwestern School-Wide Positive Behavior Supports, Western Schoolwide Positive Behavioral and Instructional Supports or Response-To-Intervention, and both the Midwestern and Western states combined) consisting of the common 28 School Implementation Scale items reveals that the 4-factor structure specified for the SIS does not adequately fit any of the datasets. The SIS, however, initially consisted of 31 items. Statistical analysis of the 2014 Midwestern state's dataset with 31 items also reveals that the data does not adequately fit the 4-factor structure specified for the SIS. Therefore, the 4-factor structure may have been an incorrectly specified model for the School Implementation Scale, and should be reviewed then revised. This study concludes that the SIS with its current 4-factor structure, for either 28 or 31 items, is not a valid and reliable measure of the implementation level of integrated academic and behavioral multi-tiered systems, and should not be used across various state populations and different forms of multi-tiered support systems. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

This quantitative study analyzed archival data to determine whether a significant difference existed in the reading comprehension scores and student success (enrollment in honors and or advanced placement classes and college after graduation) of at-risk African American male students who received Advancement via Individual Determination/African American Male Initiative (AVID/AAMI) learning modalities and those who did not. The sample consisted of 134 at-risk African American male students from a California school district. A descriptive comparative research design provided effectiveness in gathering and analyzing data to find the differences between the two groups. The results of an ANCOVA test and chi-square goodness-of-fit tests indicated no significant difference (F = 0.054, P = 0.817) between the mean gain reading comprehension scores of 11th grade at-risk African American male students who received AAMI/AVID learning methodologies and those who did not. However, a significant difference did exist (P = 0.000, chi-square = 24.605) between the two instructional approaches (AAMI/AVID learning methodologies and non-AAMI/AVID learning methodologies), which indicated a high association between AAMI/AVID learning methodologies and enrollment into more rigorous courses such as advanced placement and or honors classes: X[superscript 2](1) = 7.410[superscript a], p (0.006) = 0.05. Although a final research question (Is there a difference in the number of students enrolled in college after graduation of at-risk African American male students who received CRP and those who did not during 2010-2013?) could not be answered due to lack of available data, teachers and or administrators of the AAMI/AVID program in the district recorded that 90% of the at-risk African American male students who received AAMI/AVID learning methodologies enrolled in college after graduation. Practical implications for this study suggested that professional development (PD) of AAMI/AVID learning methodologies is an essential factor in effective implementation of AAMI/AVID learning methodologies, and these methodologies can yield positive results for at-risk African American male students. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The purpose of this exploratory study was to examine teachers' perceptions of motivational literacy instructional strategies for use with English as a second language learners (ESLs). Self-determination theory's basic psychological needs theory and organismic integration theory acted as the lens through which this topic was explored. A Likert-type quantitative survey was used to produce a ranked list of motivational metacognitive reading strategies using a chi-square goodness of fit test with effect sizes and descriptive statistical analysis (M and SD). Relative frequencies were calculated to compare strategies relative importance to teachers perceived frequency of use. Metacognitive reading strategy category trends were analyzed. Results found that effective ESL teachers tend to use global strategies more often than problem-solving and support strategies. Additionally, ESL teachers believe it is most important to develop student's feeling of competence. The study concluded that future research should examine the effects of each type of metacognitive reading strategy on student motivation and achievement to isolate critical variables. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Reading challenges are still evident for more than 90 million adults in the United States who are functioning at the lowest levels of literacy (United States Department of Education, 2004). Leveled Literacy Intervention (LLI) is one program designed to address these educational needs. The purpose of this quantitative study was to investigate the impact of LLI on reading ability when used as an early reading intervention for 2nd grade students at risk of reading failure. A random sample of reading data for 106 students was taken from the 146 2nd grade students who participated in LLI for 18 weeks. A comparison group was comprised of a random sample of reading scores for 146 students who did not receive LLI intervention. This study also examined the perceptions of the 18 teachers who used LLI for reading intervention. A quasi-experimental design was used to analyze teacher perceptions and LLI's effect on reading scores. Reading scores were measured by the Measure of Academic Progress Assessment. Reading intervention teachers' perceptions of LLI were analyzed using chi-square goodness of fit. The results of this study indicated that the reading scores of 2nd grade students who participated in LLI significantly increased. However, the comparison group that did not participate in LLI made more reading gains than the students who received LLI. The result also indicated survey data on teachers' perceptions of the effectiveness of LLI on students' reading ability, program adequacy, and material adequacy were significantly positive. The results may positively contribute to social change by providing educators with a better understanding of effective reading intervention for student in danger of reading failure. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

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. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

A structural model for prior achievement, school integration, and self-efficacy was developed using Tinto's theory of student attrition and Bandura's self-efficacy theory. The model was tested and revised using a sample of 1,452 males and females from single-sex and coeducational parochial high schools. Results indicated that the theoretically hypothesized model provided an adequate framework for understanding the relationships between the variables in the model. All paths were positive and statistically significant. Multigroup structural equation modeling (SEM) was then used to test and compare four groups from the sample: females from single-sex (n = 378) and coeducational schools (n = 303) and males from single-sex (n = 457) and coeducational schools (n = 314). In line with past studies, results of ANOVA tests showed mean level differences between groups on measures of prior achievement, school integration, and self-efficacy. The current study considered the limitations of ANOVA tests and also used multigroup SEM to compare groups, which allowed the relationships between variables to be tested. There was model invariance, as model fit was equal for all groups. These findings address gaps in the literature on single-sex education, which to date has been mixed and inconclusive, and provide new knowledge regarding the social cognitive processes in single-sex and coeducational schools. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Little is known about students' perceptions of online enrollment processes. Student satisfaction is part of the assessment required for accreditation, but evidence suggests that college administrators are oriented to retention and graduation rates rather than to consumer perception. The purpose of this descriptive quantitative study was to develop and validate a model that enables the measurement of online enrollment processes by the analysis of the students' perceptions. The theoretical framework used to support this study was the process virtualization theory while the conceptual framework was based on Technology Acceptance Model (TAM). TAM is the most valid framework for studying user acceptance of technology and virtual processes. The model was modified, adding a new variable to fit this study. Research questions were used to determine if an institution knows how its students perceive online enrollment processes and how they can become more efficient and effective, improving usage and satisfaction. Descriptive data were collected and analyzed in phases: the pilot study phase, data collection phase, and analysis phases. Inferential statistics were used to draw information from sampled observations of the population; a Cronbach Alpha was conducted to determine the reliability and validity of the model. The study demonstrated that the modified TAM is valid, reliable, and fit to assess the perceptions of the users of online enrollment processes. This study will effect positive social change by providing enrollment managers and administrators information on how to analyze the acceptance their online enrollment processes from the perspective of their students as customers of an institution of higher learning. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

This study employed Bachman and Palmer's (2010) Assessment Use Argument framework to investigate to what extent the use of a second language oral test as an exit test in a Hong Kong university can be justified. It also aimed to help test developers of this oral test identify the most critical areas in the current test design that might need improvement. Candidates' oral responses to five integrated speaking tasks in this oral test were rated on five dimensions: Task fulfillment and relevance (TFR), Clarity of presentation (CoP), Grammar and Vocabulary (GV), Pronunciation (Pron), and Confidence and Fluency (CoFlu). To provide backing for the meaningfulness of interpretations, confirmatory factor analysis (CFA) and item response theory (IRT) analyses were used to analyze 999 candidates' scores and raters' verbal reports were also analyzed to provide complementary information to the results of the quantitative analyses. Several CFA models were first tested and compared in terms of their statistical fit and substantive interpretability. And a graded response model was applied to the test data. The CFA results showed that the superior fit of the Higher-order trait-Uncorrelated Method model validated the test design, confirmed the current multicomponential view of language ability in the literature, and provided the most parsimonious explanation of the relationships among the five dimensions and overall speaking proficiency. The analytic scores were found to have much larger factor loadings on the trait factors than on the method factors, providing evidence that the component test scores could be meaningfully interpreted as indicators of the five dimensions. The presence of a higher-order speaking ability factor governing the five trait factors also supported the practice of reporting one composite score. Task Fulfillment and Relevance (TFR) measured on Task 4 had the highest method loading (0.60) on Task 4 and the lowest trait factor loading (0.36) on TFR, which suggested TFR4 might be too task specific and weak in measuring students' speaking ability to fulfill a speaking task in a relevant way. The trace lines of the graded response model also confirmed this. The raters' verbal reports showed that most raters did not have much difficulty differentiating across the performance levels. Hence, the problem of TFR4 can only be due to the nature of the task itself and its low discrimination. Both CFA and IRT results indicated that task types had great effects on test takers' speaking abilities especially TFR and that this language ability component might be too task specific. In order to investigate the impartiality of interpretations, multi-group CFA and differential item functioning (DIF) were conducted to examine the extent to which the oral test had test bias and item bias across (1) gender and (2) disciplines. The multi-sample CFA results indicated that the factor structure was significantly different between males and females. However, the comparison of the factor loadings between females and males showed that only the factor loading of one item for the male group was significantly different from the female group at the 0.05 level. DIF results also suggested that the majority of the items displayed no DIF. The source of DIF may be attributed to the group mean difference on the latent trait and their real differences on certain aspects of language ability measured in this test. This provided backing for the impartiality of score interpretations, indicating that the rating-based interpretations from GSLPA SLT are impartial to a large extent across subgroups of test takers (males vs. females; business vs. non-business). In order to examine the consistency of test scores, Generalizability theory (G theory) analyses were performed to investigate whether the test was dependable and whether the five dimensions were separable. G theory results showed that the phi coefficient for the whole test fell between 0.76 and 0.85 and Grammar and Vocabulary and Pronunciation proved to be the most dependable dimensions. G theory and CFA results both confirmed that the five speaking dimension were highly correlated with each other. The possible reasons of these findings were further discussed with reference to the raters' verbal reports. Based on the above results, it can be concluded that the meaningfulness, impartiality, and consistency could be justified to a large extent. Some critical areas to be improved in the test design and administration were identified. Theoretical and practical implications were addressed and methodological limitations were also discussed. Overall, this study highlights the usefulness of Bachman and Palmer's Assessment Use Argument (2010) to justify the use of an existing language assessment. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The present study sought to fit a cognitive diagnostic model (CDM) across multiple forms of a passage-based reading comprehension assessment using the attribute hierarchy method. Previous research on CDMs for reading comprehension assessments served as a basis for the attributes in the hierarchy. The two attribute hierarchies were fit to data from three forms of a large-scale assessment, one consisting of nine attributes and the other eleven attributes. Model-data fit of the two models was evaluated to determine if a single model of reading comprehension could be applied to multiple operational testing forms. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Among higher education faculty, having to address academic misconduct and plagiarism is often viewed as a negative aspect of teaching resulting in inconsistent reporting by faculty. Some faculty members take no action in response. Differences exist in attitudes between traditional regular full-time and part-time adjunct faculty members in terms of plagiarism. With the growing use of part-time adjunct faculty to meet the demands for online learning, a fuller understanding of the influences on reporting of student plagiarism among faculty members teaching online is needed to expand the knowledge base about student plagiarism. The purpose of this quantitative nonexperimental study was to examine whether any differences or relationships existed among regular full-time faculty members and part-time adjunct faculty members who teach at least one class online related to reporting student plagiarism in terms of the variables from the theory of planned behavior (TPB). A survey design with hypothesis testing, correlational, and regression analyses was used. Approximately 651 faculty members who teach at least one class online, including 180 regular full-time faculty members and 471 part-time adjunct faculty members from two different Midwestern universities were invited to voluntarily complete the Faculty Reporting Plagiarism Questionnaire (FRPQ). This researcher-developed questionnaire was constructed from modifications made to previously published scale content, reflective of the TPB variables: intention, attitudes, subjective norms, and perceived control. Factor analysis was performed to examine goodness-of-fit of the FRPQ items to TPB. Adequate power for two-tailed t-tests of independent samples was obtained with 156 completed questionnaires (43 [24%] from regular full-time faculty members and 113 [24%] from part-time adjunct faculty members). No significant differences were seen between regular full-time and part-time adjunct faculty members for intention (p = 0.811), attitude (p = 0.863), subjective norms (p = 0.443), and perceived control (sig. = 0.097). No significant correlations were seen among the TPB variables in terms of employment appointment: attitude ( r[subscript pb] = -0.014; p = 0.863), subjective norm (r[subscript pb] = -0.062; p = 0.443), and perceived control (r[subscript pb] = -0.034; p = 0.673. With no differences seen, the needed discussions and training regarding reporting student plagiarism can take place equally with both groups. Fit indices demonstrated mixed results for goodness-of-fit of the FRPQ dataset with the TPB variables. Further research is indicated with the mixed fit indices to further examine the FRPQ and TPB. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Response to intervention (RtI) is an approach to assist students with learning difficulties. There is limited research into the effectiveness of RtI within rural school districts. To address that gap, this quantitative, experimental study tested the theory of RtI, comparing the tier of intervention to oral reading fluency, controlling for classroom, school, educational leadership, teacher, and other students for the evaluated students at 2 rural elementary schools. The key research question investigated how the RtI theory explained the difference between students who receive intervention at Tier II as compared to students who receive intervention at Tier III? For the current study, a hierarchical linear model was used to determine the impact of different tiers of instruction on oral reading fluency rate of improvement. The results indicated that school of attendance and tier of instruction were significant in determining the impact of the intervention program on students' rate of improvement for oral reading fluency. The best fitting model for predicting rate of improvement of oral reading fluency scores was a linear combination of the tier of instruction and school of attendance (R = 0.173, R[superscript 2] = 0.030, F (5,394) = 2.399, p < 0.05). Social change implications include the provision of appropriate reading instruction for children in a rural environment, the need for increasing school staff, and changing the role of psychologists. These changes will enable school districts and state and local education departments to appropriately address the needs of students, thus ensuring optimal outcomes. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The purpose of this quantitative inferential study is to determine the level of correlation between the organizational factors of information security awareness, balanced security processes, and organizational structure with the size of the estimation gap of information security implementations mediated by the end user intentionality. The study used structural equations modeling (SEM) to assess the goodness of fit of the proposed model with the information technology executives and professionals of the government of the Commonwealth of Puerto Rico. The SEM analysis confirmed a very good fit of the proposed model with the sample data from the target population. The model provided the information to confirm the significant correlations between the organizational factors with the user intentionality factor, and between the user intentionality and the size of the estimation gap. Also, the study confirmed a partial mediating role of the user intentionality between the organizational factors and the size of the estimation gap. The study offers recommendations to governmental executives about a way to lower the estimation gap on information security implementation projects. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The Common Core State Standards for English Language Arts (CCSS-ELA) will have a significant impact on what teachers teach and what primary students are supposed to be able to do (Bomer & Maloch, 2011). By the end of fourth grade, reading instruction should be evenly balanced between literary text and informational text (NGA Center and CCSSO, 2010b). The purpose of this quantitative content analysis study was to compare the percentage of informational text found in the three most widely purchased, commercially published fourth grade basal reading texts ("Journeys" published by Houghton Mifflin Harcourt [2011], "Treasures," published by MacMillan/McGraw-Hill, [2011], and "Reading Street," published by Scott Foresman [2012]) with the informational text recommendations of the CCSS-ELA (NGA Center and CCSSO, 2010b). Coding of informational vs. literary text in these commercial textbooks followed Krippendorff's (1980) definitions and analytical framework which yielded percentage breakdown of informational text into the following subcategories: expository text, argumentative or persuasive text, and procedural text or documents. Results demonstrated that none of the three commercial texts met CCSS-ELA standards of informational text. The percentage of selections devoted to informational text ranged from 28%-33% (mean = 31%) across publishers. The percentage of pages devoted to informational text ranged from 15%-18% (mean = 16.6%) across publishers. A chi square goodness-of-fit test revealed a significant difference in the observed frequencies of informational text in the commercial texts and the expected frequencies of 50% derived from the CCSS-ELA standards (p-value less than a = 0.05). The results indicated that the percentage of informational text found in the student text of the three most widely purchased fourth grade basal readers does not meet the informational text standard set for fourth grade by the CCSS-ELA (NGA Center and CCSSO, 2010b). [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The purpose of this case study was to examine the School-Wide Positive Behavior Support (SWPBS) impact on five selected student performance factors. A literature review revealed there have been many SWPBS research studies regarding traditional public schools. However, there have not been any published empirical SWPBS studies involving K-12 alternative public schools. Addressing this gap in the literature a Midwestern K-12 alternative public school involving 1,164 students was studied 2007-08 through 2010-11. Data were collected through several school information systems including School Administration Student Information System (SASI), School-Wide Information System (SWIS), and Power School. The independent variable SWPBS was investigated regarding its impact on the five dependent variables academic achievement, attendance, office discipline referrals, dropout rate, and persistence to graduation. Frequencies and percentages of each variable were analyzed using the Chi-square "goodness of fit" test (field, 2009). Previous studies at traditional public schools reported SWPBS positively impacted the five student performance factors, however this case study did not yield any significant findings at the K-12 alternative public school. Specifically, there were no significant differences between the first year when there was no SWPBS and the fourth year when SWPBS was fully implemented. These outcomes raised more questions than answers. (a) Do the students at K-12 alternative public schools require a different three-tiered level system as compared to those in the traditional public schools? (b) Does the process of advancing from one level to another take a longer time for these students? (c) Does professional development need to focus more on how to provide SWPBS strategies to at-risk and special needs students at K-12 alternative public schools? (d) Does the plan of gradually working through the SWPBS initial stages to full implementation take more years for the K-12 alternative public schools to achieve? Since there are no empirical studies for K-12 alternative public schools to use as guides, future research is essential to answers these questions. The findings and conclusions of this case study will guide building level and school district leaders as they continue the quest for programs and strategies to enhance positive student behavior and academic success. Implications are addressed and recommendations made for further research. The dissertation findings will also add to the gap in the literature and provide a springboard for future research regarding SWPBS effects at alternative public schools. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The primary purpose of this study was to determine if urban preschool decreased the likelihood of future identification of learning disabled (LD). According to the Child Development Institute (2010) and the Learning Disabilities Association of America (2010), four to ten percent of the school-aged students in this country are learning disabled. The quantitative research methodology employed a causal-comparative design using archival data collected from the questionnaires completed by parents/guardians within one urban city in the United States. This study explored 49 students that had been identified as LD, attended an urban elementary school and were in grades one to five. The collected data for this study concludes that the completion of public preschool appears to decrease the likelihood of future identification of LD. The results of the statistical test, chi square goodness to fit, indicated that there was a significant difference between the completion of public preschool and the future identification of learning disabled. In addition, the results revealed that there was a significant difference between the number of children who had completed public preschool and attended first grade without a learning disability and the number of children who had not completed public preschool and attended first grade with a learning disability. The chi square goodness to fit implied that there was a statistically significant difference between the number of children identified as learning disabled during the elementary school years (grades one to five) who had completed public preschool and the number of children identified as learning disabled during the elementary school years (grades one to five) who had not completed public preschool. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

In order for schools to be successful in providing students with developmentally appropriate instruction and social experiences, an atmosphere of safety and protection is required. The recent spike in school shootings over the past 15 years has created a sense of urgency to examine the dynamics of school violence in order to generate and implement effective security measures (Brooks, Schiraldi, & Ziedenberg, 2000). Unlike traditional problem-focused approaches, the positive approach to school violence is preventive, solution-driven, and systemic. The positive approach to violence prevention at school focuses on building a set of social and emotional strengths that are incompatible with antisocial behavior. Recently researchers have focused on determining the positive behaviors that could potentially stop aggressive situations from progressing. These helping behaviors are defined broadly as prosocial behaviors (Cashwell, Skinner, & Smith, 2001; Goldstein, Carr, Davidson, & Wehr, 1981; Greener, 2000; Leffler & Snow, 2001). Research on child development suggests that one of the most effective ways for school to encourage prosocial behavior is through school-wide programs designed to teach and model social skills. The current study sought to evaluate the effectiveness of a comprehensive school wide prevention program intervention called "Be a Safety Kid" in kindergarten through third grade students. It also sought to assess the validity and stability over time of the corresponding pretest/post-test measure termed, the S.T.A.R. instrument. Results of a confirmatory factor analysis (CFA) suggested that the three factor structure of the S.T.A.R. instrument remained stable overtime and but inconsistently described the data for the first, second, and third grade instruments. CFA results from the kindergarten S.T.A.R. instrument indicated a poor fit based on the data collected. Repeated measure ANOVA results indicated students showed significant improvement in prosocial knowledge and anticipated ability to demonstrate prosocial behaviors after receiving the "Be a Safety Kid" curriculum; however, no significant improvement in perception of school safety was observed. Outcomes discussed add to the existing literature of evidence-based practices designed to reduce violence in the school environment. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

This mixed-methods study is represented by three articles that examine student achievement. The articles were developed based on the following purposes: (1) to examine teachers' conceptions about student achievement; (2) to examine teacher practices for school improvement that reflects elements of a reform model; and (3) to examine teachers' conceptions about school improvement challenges. Individual interviews were administered to examine teachers' conceptions about student achievement and school improvement challenges. The conceptions were then converted to excerpts that were grouped into common categories. Common descriptive categories were developed using the methodological framework, phenomenography. To examine teacher practices that reflect elements of a reform model, the researcher used classroom observations. The classroom observations were analyzed using a Classroom Observation Protocol that determined the frequency of teacher practices that reflect elements of the 90/90/90 Model. The study also examined MEAP test scores using the chi-squared goodness-of-fit test to compare the 2009 and 2010 results. To address the first purpose of the study, three descriptive categories were revealed based on the data. The three categories were: (1) analyzing student achievement data to develop interventions; (2) a model to decrease disruptive behavior; and (3) parent involvement to support children's learning. To address the second purpose of the study, the results revealed that of the five elements, teacher practice displayed three elements: (1) the focus on academic achievement; (2) the choice of curriculum; and (3) the frequent use of multiple assessments. The third purpose of the study was addressed by the emergence of three descriptive categories from the data. The three categories are as follows: (1) student transiency throughout the school year; (2) staff restructure and transfers to different schools; and (3) lack of parent involvement in school and at home. In addition, the results of the chi-squared test revealed a significant difference between the observed (2010) and expected (2009) MEAP Test scores. The following implications emerged from the results of the study: (1) a practical reform model for school improvement that is anchored in a theory of curriculum can be used as a lens to view student achievement; (2) school districts that incorporate teachers' conceptions about student achievement are able to make effective curriculum-based decisions; (3) school districts that identify the intra- and inter-variations of teacher conceptions enable schools to address challenges with a common mindset; (4) in order for schools to improve student achievement, all five elements of the reform model should be practiced by teachers; and (5) teachers' conceptions of school improvement challenges should be considered by educational leaders during the decision-making process. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

In the present study, an attempt was made to determine the degree to which psychologists at college and university counseling centers (UCCs) utilized empirically supported treatments with their posttraumatic stress disorder (PTSD) clients. In addition, an attempt was made to determine how frequently UCC psychologists utilized a number of evidence-based practice resources with a wide range of clients. The Trauma Practices Questionnaire (Craig & Sprang, 2009, 2010; Sprang & Craig, 2007), the author-generated Treatment Approaches Routinely Utilized with PTSD Clients Questionnaire, the Evidence-Based Practice Questionnaire (modeled after a survey by Mullen & Bacon, 2006), and the author-generated Demographic and Professional Information Questionnaire were administered on an Internet survey website to participants recruited through advertising on a social networking website or contacted via email. One hundred and ten participants, including 83 women and 27 men, were included in the final results. A repeated measures analysis of variance (ANOVA) with Least Significant Difference post-hoc tests showed significant differences between psychologists' utilization of cognitive therapy (CT), behavioral therapy (BT), and eye movement desensitization and reprocessing therapy (EMDR) with PTSD clients. A chi-square goodness of fit test showed that the majority of psychologists did not regularly utilize exposure therapy with their PTSD clients. In addition, a chi-square goodness of fit test indicated that the majority of psychologists rarely utilized treatment manuals with a wide range of clients. Lastly, chi-square goodness of fit tests showed that a significant proportion of psychologists did not refer to the practice guidelines from the International Society for Traumatic Stress Studies (ISTSS) when treating PTSD clients, but that a much higher percentage of psychologists had utilized at least one set of practice guidelines over the course of their career. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The Preliminary SAT/National Merit Scholarship Qualifying Test (PSAT/NMSQT) is a test jointly administrated by the College Board and National Merit Scholarship Corporation, which is used to prepare high school students for the SAT, and as initial screening for numerous scholarships (Marini, Mattern, & Shaw, 2011). Previous research has acknowledged that the PSAT/NMSQT measures student's critical reading skills, quantitative reasoning, and writing skills related to academic success in college (Camara, 1998). Therefore, there is a substantial number of students who choose to retake the test in the subsequent year. The purpose of this study was to provide information about how test scores change in each component of the test (i.e. the PSAT-CR the PSAT-M, and the PSAT-W) when students retake the PSAT as well as to explore what factor influence the change in the test scores. Two cohorts of data were provided by the College Board--students who graduated from high school in 2008, and in 2009. For these students, up to four testing occasions were available in the data along with numerous demographic and educational variables. Latent growth modeling (LGM) was employed to examine the trends in the individual trajectories of the PSAT-CR, the PSAT-M, and the PSAT-W. A series of unconditional models, models conditional on policy covariates, and models conditional on policy and educational covariates were fit to the data. Models assuming linear growth fit well in the PSAT-CR and the PSAT-M components of the test. The fit was less adequate for the PSAT-W. Gender and ethnicity emerged as significant predictors of the score obtained in the freshman year as well as the rate of change. The strongest educational predictor was writing ability. Results obtained from this longitudinal research are theoretically and practically informative for understanding the magnitudes of score change in the PSAT and the processes that are behind this change. Information on score change when the test is taken repeatedly may help students, teachers, test developers and test administrators to make better-informed decisions about testing students. Moreover, this information may also help parents and counselors who advise students on how to prepare for the test and whether to retake it. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Rapid changes in mobile techniques have always been evolutionary, and the deployment of 4G Long Term Evolution (LTE) networks will be the same. It will be another transition from Third Generation (3G) to Fourth Generation (4G) over a period of several years, as is the case still with the transition from Second Generation (2G) to 3G. As a result, mobile operators must look for strategies and solutions that will enhance their legacy 3G networks, while addressing their 4G deployment requirements without involving a "forklift" upgrade. Mobile subscribers have a certain expectation for their experience of mobile data and voice services that the wireless environment has not fully met yet since the speed at which they can access their mobile services has been limited. On the other hand, mobile operators realize that if they are to succeed in today's mobile communications landscape, they must address the quality of service for their subscribers. Simply adding more bandwidth to accommodate increased traffic is an expensive alternative. How to do more with less? The mobile operators need to minimize Capital Expenditure/Operation Expenditure (CAPEX/OPEX) and maximize subscriber usage. They need to ensure that the mobile network is operating optimally over their capacity planning horizon and make further capital investment in expanding the network infrastructure when the Quality of Service (QoS) falls below their set goal based on the customer expectations. Hence the time to upgrade the core network should coincide with the investment planning horizon. However, since the deployment of 4G LTE networks is a new challenge technically, there are still some unanswered questions on how to dimension the 4G LTE networks for a given scenario and predict the traffic of 4G LTE networks in a long term. The purpose of this research is to study the traffic planning and performance modeling for the evolved packet core networks of LTE network. I created the quantitative algorithms to dimension the traffic for 4G LTE networks. The algorithms emulated the differentiated services (DiffServ) over the 4G LTE networks and applied the DiffServ, via the Weighted Fair Queuing (WFQ) scheduling technique, to the specific traffic flow models (M/G/R-PS and M/D/1-PS) which handle different types of traffic (elastic traffic and streaming traffic) in the 4G LTE network. Furthermore, in order to forecast the chronically increased traffic of 4G LTE networks, I created the algorithms to trend the 4G LTE network traffic via training the historical network performance data This will provide the modeling capability for the mobile operators to plan their capacity increase to match their capital investment horizon and maintain their desired QoS throughout this horizon. Several quantitative algorithms have been applied to train the measured network performance data to find the optimal adjusted threshold of network capacity. After the testing on the reliability, robustness, and external validity, it is concluded that the approach of an improved stochastic gradient boosting shows the best goodness of fitting for calibrating the model for the least prediction error in forecasting the prospective traffic for the next planning horizon. The mobile operators need to minimize their CAPEX/OPEX while planning their network expansion to meet their desired level of service quality. Optimizing investment in the evolution of the 4G network is a limitation of the current research. In particular the CAPEX is determined by the specific network equipment and vendors that the mobile operator uses in planning its networks. I have outlined the steps necessary to conduct the cost analysis in conjunction with the network planning and dimensioning based on specific planning scenario to allow the mobile operators to evaluate their alternative investment options. A case study is provided in the Appendix to approximately estimate the CAPEX/OPEX for a given network scenario. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Three decision consistency and accuracy (DC/DA) methods, the Livingston and Lewis (LL) method, LEE method, and the Hambleton and Han (HH) method, were evaluated. The purposes of the study were: (1) to evaluate the accuracy and robustness of these methods, especially when their assumptions were not well satisfied, (2) to investigate the "true" DC/DA indices in various conditions, and (3) to assess the impact of choice of reliability estimate on the LL method. Four simulation studies were conducted: Study 1 looked at various test lengths. Study 2 focused on local item dependency (LID). Study 3 checked the consequences of IRT model-data misfit and Study 4 checked the impact of using different scoring metrics. Finally, a real data study was conducted where no advantages were given to any models or assumptions. The results showed that the factors of LID and model misfit had a negative impact on "true" DA index, and made all selected methods over-estimate DA index. On the contrary, the DC estimates had minimal impacts from the above factors, although the LL method had poorer estimates in short tests and the LEE and HH methods were less robust to tests with a high level of LID. Comparing the selected methods, the LEE and HH methods had nearly identical results across all conditions, while the HH method had more flexibility in complex scoring metrics. The LL method was found sensitive to the choice of test reliability estimate. The LL method with Cronbach's alpha consistently underestimated DC estimates while LL with stratified alpha functioned noticeably better with smaller bias and more robustness in various conditions. Lastly it is hoped to make the software be available soon to permit the wider use of the HH method. The other methods in the study are already well supported by easy to use software. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

This study compared the model-data fit of a parametric item response theory (PIRT) model to a nonparametric item response theory (NIRT) model to determine the best-fitting model for use with ordinal-level alternate assessment ratings. The PIRT Generalized Graded Unfolding Model (GGUM) was compared to the NIRT Mokken model. Chi-square statistics were examined to determine the fit of the GGUM. To determine the fit of the Mokken model, Loevinger's H coefficients and the number of monotone homogeneity (MH) and double monotonicity (DM) violations were examined. Participants were 4,449 students ages 7 to 21 with autism spectrum disorder, a mild intellectual disability, moderate intellectual disability, or severe intellectual disability. These students participated in Indiana's alternate assessment, the Indiana Assessment System of Educational Proficiencies (IASEP) in the years 2000, 2001, or 2002. The IASEP consists of five subscales, consisting of 20 items, each, in the domains of Information Acquisition and Use (Language Arts and Math), Personal Adjustment, Social Adjustment, Recreation and Leisure, and Vocational Experience. Students are rated by teachers using a universal rubric ranging from 0 to 4. The GGUM showed better overall model-data fit with most items showing good fit across all disability groups. The Mokken model's stricter assumption of double monotonicity (DM) did not hold. The Mokken model's required property of monotone homogeneity (MH) held across most items and disability groups, making this model useful for selected applications. Researchers or practitioners may benefit when choosing which IRT model to use for alternate assessment ratings. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The purpose of this study was to investigate procedures for assessing model fit of IRT models for mixed format data. In this study, various IRT model combinations were fitted to data containing both dichotomous and polytomous item responses, and the suitability of the chosen model mixtures was evaluated based on a number of model fit procedures. To assess model fit for mixed format data, five fit indices were considered: PARSCALE's G[superscript 2], the generalized forms of Orlando and Thissen's (2000) S-X[superscript 2] and S-G[superscript 2], and Stone's (2000) pseudo-observed score based indices chi[superscript 2*] and G[superscript 2*]. To investigate the relative performance of the five item fit statistics, two simulation studies were conducted: Type I error and power studies. Using the model hierarchy for a set of the data generation models and calibration models, model-fitting and model-misfitting conditions were manipulated to obtain Type I error rates and power. Under the model-fitting conditions, Type I error rates were computed when identical pairs of mixed IRT models were used for data generation and calibration. On the other hand, empirical power was calculated under the model-misfitting conditions when data were calibrated using a simpler model than a generating model. Among the competing measures, the number correct score based indices S-X[superscript 2] and S-G[superscript 2] were found to be the most efficient and safest choice for assessing model fit for mixed format data across the study conditions. These indices performed well particularly with short tests. However, the pseudo-observed score indices, chi[superscript 2*] and G[superscript 2*], showed inflated Type I error rates in some simulation conditions. Thus, their applications appeared to be limited by specific measurement conditions, and need to be studied further for generalized uses. Consistent with the findings of current literature, the PARSCALE's G[superscript 2] index was rarely useful, although it provided reasonable results for long tests. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

The purpose of this quantitative correlational research study was to investigate, describe, and measure factors influencing retention of nontraditional first and second year students at a university located in the Midwestern United States. Retention of adult students has become a major issue for many institutions of higher education and many educational leaders are interested in developing strategies that facilitate the student success. Four constructs from the theory of planned behavior (TPB) were used to create a predictive model of continued university enrollment (Retention). The relationships between attitudes about studying (Attitude), subjective social norms (Norms), behavioral intention (Intention), and perceived behavior control (Control) and Retention were tested by five statistical hypotheses. Through simple random sampling, 133 students from a pool of currently enrolled and withdrawn students from the university participated; 116 of these were included in the analysis. Data analysis included structural equation modeling with exploratory and confirmatory factor analyses and common method variance. Although the results revealed a strong model fit, underlying measurements were weak (NFI = 0.10, NNFI = 0.99, CFI = 0.10, and RMSEA = 0.60) and did not meet preset parameters for goodness-of-fit and thus the model was rejected. Attitude was the only scale of the four variables that contained sufficient construct validity to represent a valid and reliable measure; Attitude positively correlated to Retention (r = 0.33, p less than 0.05). Female gender was the only demographic characteristic of significant contribution to the model. The TPB provides a framework from which to begin looking at factors that influence student Retention. Further revision and testing of the survey questionnaire are recommended. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]

Measurements of social constructs that evaluate natural hazard preparedness are important to decrease natural hazard vulnerability. Preparedness reduces natural hazard impacts and human vulnerability. Investment in education and education research contribute to human sustainable development and natural hazard preparedness. Faced with other needs, people typically do not prepare enough to reduce the potential impacts of infrequent but potentially catastrophic natural hazard events. Consequently, human vulnerability increases over time and space. Specifically, natural hazards such as tsunamis and earthquakes (Colombia 1979; Sumatra (Indonesia) 2004), hurricanes (Katrina 2005, U.S.), volcanoes (Nevado del Ruiz 1985, Colombia), floods (Venezuela 1999), and fires (Southern California 2007, U.S.) can exact a tremendous toll on both lives and property (United Nations: International Strategy for Disaster Reduction (ISDR), 2009). Yet, most damage from natural hazards can be mitigated or even avoided in great extent with proper preparedness. Why, then, do so few people take precautions? Furthermore, how can we induce major levels of preparedness? This research postulates a conceptual framework that takes into account the learning theory of Paulo Freire. The main objective of this research is to establish the initial validity and reliability of a new social construct measurement (TOTPI) that is accountable for tracing transformative optimism beliefs that impact behaviors related to tsunami hazard preparedness on the United States Pacific Northwest Coast, using exploratory structural equation models (ESEM). The final SEM model for TOTPI, with maximum likelihood parameter estimator, had a multiple correlation of R = 0.543 (R[superscript 2] = 0.30) between the predictors Transformative Optimism (T.O.), Resilient Optimism (R.O.), and Fatalistic Optimism (F.O.); and the current tsunami preparedness (criterion), this means that 30% of the current tsunami preparedness variance is explained by the T.O., R.O. and F.O. factors. The Chi-square is 355.26 with 126 degrees of freedom. The Comparative Fit Index (CFI) is 0.92; TLI is 0.91; the Root Mean Square Error of Approximation (RMSEA) is 0.060 with RMSEA 90% C.I. between 0.053 and 0.068; and the Standardized Root Mean Square Residual (SRMR) is 0.051. This appears to be a good fit to the observed data according to Hu & Bentler (1999) as cited in Kline (2005, p. 140), and according to Browne & Cudek (1993, p.144) as cited in Brown (2006, p. 87). [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]