Full weighted least squares (full WLS) and robust weighted least squares (robust WLS) are currently the two primary estimation methods designed for structural equation modeling with ordinal observed variables. These methods assume that continuous latent variables were coarsely categorized by the measurement process to yield the observed ordinal variables, and that the model proposed by the researcher pertains to these latent variables rather than to their ordinal manifestations. Previous research has strongly suggested that robust WLS is superior to full WLS when models are correctly specified. Given the realities of applied research, it was critical to examine these methods with misspecified models. This Monte Carlo simulation study examined the performance of full and robust WLS for two-factor, eight-indicator confirmatory factor analytic models that were either correctly specified, overspecified, or misspecified in one of two ways. Seven conditions of five-category indicator distribution shape at four sample sizes were simulated. These design factors were completely crossed for a total of 224 cells. Previously findings of the relative superiority of robust WLS with correctly specified models were replicated, and robust WLS was also found to perform better than full WLS given overspecification or misspecification. Robust WLS parameter estimates were usually more accurate for correct and overspecified models, especially at the smaller sample sizes. In the face of misspecification, full WLS better approximated the correct loading values whereas robust estimates better approximated the correct factor correlation. Robust WLS chi-square values discriminated between correct and misspecified models much better than full WLS values at the two smaller sample sizes. For all four model specifications, robust parameter estimates usually showed lower variability and robust standard errors usually showed lower bias. These findings suggest that robust WLS should likely remain the estimator of choice for applied researchers. Additionally, highly leptokurtic distributions should be avoided when possible. It should also be noted that robust WLS performance was arguably adequate at the sample size of 100 when the indicators were not highly leptokurtic. / text

The Outcome Questionnaire (OQ-45; Lambert et al., 1996) has been widely employed as a psychotherapy outcome monitoring measure following research findings that support various aspects of its validity and sensitivity to change. Despite its broad usage in both clinical and research settings, some of its psychometric properties are not definite. The three subscales of the OQ-45 are designed to measure three distinct, but related, aspects of psychological functioning. However, neither the one- nor three-factor models have been supported by previous research. Likewise, the results of the current study supported neither of those factor structures. It was suspected that heterogeneity in data might have led to the lack of the confirmatory factor analysis model fit. Therefore, factor mixture modeling (FMM), a combination of confirmatory factor analysis and latent class analysis, was employed to investigate potential heterogeneity of the data. Among the series of factor mixture models with varying numbers of classes that were fitted, the two-class, unconditional FMM based on the revised three-factor solution was decided to best describe the data under analysis. Although three covariates of clinical status, sex, and race were selected as known sources of heterogeneity and incorporated into the FMMs (i.e., conditional model), the findings were contradictory to expectations. The implications of these findings in counseling were discussed in terms of aggregating OQ-45 scores and its score interpretation. Furthermore, this study demonstrates the process involved and dilemmas encountered in choosing the best fitting FMM. There is currently no criterion for assessing individual model fit. Instead, models’ fit are compared using various information criteria (IC). And, as was found in the current study, these ICs are frequently contradictory. Thus, the process of identifying the best fitting model cannot rest solely on fit indices but must also depend on interpretation of models and consideration of the ultimate use of the results. In the current study, consideration of transition matrices and the pattern of latent means across classes contributed as much to model selection as fit index interpretation. / text

The purpose of this research is to identify the factors that influence organizational insiders to violate information security policies. There are numerous accounts of successful malicious activities conducted by employees and internal users of organizations. Researchers and organizations have begun looking at methods to reduce or mitigate the insider threat problem. Few proposed methods and models to identify, deter, and prevent the insider threat are based on empirical data. Additionally, few studies have focused on the targets or goals of the insider with organizational control as a foundation. From a target perspective, an organization might be able to control the outcome of a malicious insider threat attack. This research applied a criminology lens as an organization policy violation is, or resembles, a criminal activity. This research uses the Routine Activities Theory (RAT) as a guide to develop a theoretical model. The adoption of RAT was for its focus on the target and the protective controls, while still taking into account the motivated offender. The study identified the components of the model concerning insider threats, espionage, and illicit behavior related to information systems through literature. This led to the development of 10 hypotheses regarding the relationships of key factors that influence malicious insider activity. Data was collected using a scenario-based survey, which allowed for impartial responses from a third-person perspective. This technique has become popular in the field of criminology, as the effects of social desirability, acceptance, or repudiation will not be a concern. A pilot test verified the survey's ability to collect the appropriate data. The research employed Structural Equation Modeling (SEM) and Confirmatory Factor Analysis (CFA) techniques to analyze and evaluate the data. SEM and CFA techniques identified the fit of the model and the factors that influence information security policy violations. The result of the analysis provided criteria to accept the hypotheses and to identify key factors that influence insider Information System policy violations. This research identified the relationships and the level of influence between each factor.

The psychometric properties of a parent-completed developmental questionnaire for children at 6 years of age were investigated. Currently, few developmental screening instruments for 6-year-old children have been validated, and most available instruments are designed to be completed by teachers or professionals, who may not witness an optimal sample of child behavior. Thus a screening tool with robust psychometric properties is needed that can be completed by parents or caregivers who see the child across settings and time. A total of 169 children participated in this research. Data collection included online and paper completion during well child visits, in clinics, at preschool programs, and in parents' homes. A random subsample was asked to participate in reliability and convergent validity studies. Cronbach's alpha coefficient was used to measure internal consistency reliability. Results indicated a Cronbach alpha of agreement with the Child Development Inventory was used. A Confirmatory Factor Analysis with categorical data confirmed the 6-Year Ages and Stages Questionnaire domains, e.g., communication, personal social, fine motor, gross motor, and problem solving. Limitations of the current study and directions for future research are discussed. / 10000-01-01

Social action and communication constitute the building blocks in the organizational structure and the agents of change, as well as shape the relationships among working parties, that can become inconsistent, due to the same desire of two or more people for a similar resource which is in scarcity, introducing the issue of human relations in an organizational context and especially the issue of conflict prevention. In this study we investigate conflict in a group based on different parameters by providing some insights on what is the impact between these different factors when interrelated. The research is carried out by adopting the survey path and performing multivariate statistical analysis techniques where we simultaneously examine the relationship between latent factors in an organizational conflict environment.

abstract: The tendency for psychopathology to aggregate within families is well-documented, though little is known regarding the level of specificity at which familial transmission of symptomology occurs. The current study first tested competing higher-order structures of psychopathology in adolescence, indexing general and more specific latent factors. Second, parent-offspring transmission was tested for broadband domain specificity versus transmission of a general liability for psychopathology. Lastly, genetic and environmental mechanisms underlying the familial aggregation of psychopathology were examined using nuclear twin-family models. The sample was comprised of five hundred adolescent twin pairs (mean age 13.24 years) and their parents drawn from the Wisconsin Twin Project. Twins and parents completed independent diagnostic interviews. For aim 1, correlated factors, bifactor, and general-factor models were tested using adolescent symptom count data. For aim 2, structural equation modeling was used to determine whether broadband domain-specific transmission effects were necessary to capture parent-offspring resemblance in psychopathology above and beyond a general transmission effect indexed by the latent correlation between a parental internalizing factor and offspring P-factor. For aim 3, general factor models were fitted in both generations, and factor scores were subsequently extracted and used in nuclear twin-family model testing. Results indicated that the bifactor model exhibited the best fit to the adolescent data. Familial aggregation of psychopathology was sufficiently accounted for by the transmission of a general liability. Lastly, the best fitting reduced nuclear twin-family model indicated that additive genetic, sibling-specific shared environmental, and nonshared environmental influences contributed to general psychopathology. Parent-offspring transmission was accounted for by shared genetics only, whereas co-twin aggregation was additionally explained by sibling-specific shared environmental factors. Results provide novel insight into the specificity and etiology of the familial aggregation of psychopathology. / Dissertation/Thesis / Masters Thesis Psychology 2019

Innovative people seize the opportunity to make lives better and more comfortable, which contribute to economy growth and financial gain. Stakeholders study innovativeness of business students, in depth, to understand gender differences, and the factors affecting students' innovativeness. Literature explains how males and females differ in their proneness to guilt and shame. However, a model that explains the dynamic of guilt, shame, and gender on innovativeness will help make policies to improve students' innovativeness. This study describes factor analysis approach to examine the TOSCA-3 subscales guilt, shame, and the DNA instrument of innovativeness. It also describes the measurement invariance across gender for each construct, and for the full measurement model to identify the differences between genders. Moreover, this study examines the total effect of gender on innovativeness, which includes the direct effect, and indirect effect via guilt and shame. The results indicated that guilt is positively associated with innovativeness, and shame and gender are negatively associated with innovativeness. This dissertation can be freely accessed and downloaded from (http://etd.byu.edu/).

More than 8 million of America's middle and high school students are struggling readers. Two-thirds of all eighth graders read below grade level, and the reading scores of high school students have not improved since 1974. Low literacy levels affect learning in all subject areas and impede student opportunity for future success. The No Child Left Behind Act of 2001 and the accountability measures associated with the Act have heightened public awareness of the deficiency in adolescent literacy. School districts are choosing to respond in one of two ways. Some school districts are opting to invest in teacher-proof curricula that negate the effect of the teacher. Other districts are opting to invest in the professional development of their teachers. The goal of this study was to support district efforts to provide strategic professional development opportunities for teachers by investigating the effects of teacher efficacy for instructional strategies, classroom management and student engagement on ninth and tenth grade students' reading achievement. Teachers with high efficacy were hypothesized to impact students' reading gains positively. Student contextual variables of prior achievement, socioeconomic status, ethnicity and grade were controlled for in the study. The participants included 2,061 students in 23 classrooms taught by 110 teachers in two school districts on the west coast of Florida. The results indicated that there was no statistically significant relationship between teacher efficacy and student reading achievement gains. The only variables of statistical significance were race (white vs. Non-white) and grade. As more researchers use the findings and recommendations from this study to inform new investigations of the complex relationship between teacher efficacy and student achievement in reading, teacher educators, policymakers, teachers and administrators will be better informed as they continue to work towards improving the reading achievement scores of and narrowing the achievement gaps in adolescent literacy.

The aim of this thesis was to describe fatigue, functional limitations due to fatigue and health in patients with chronic obstructive pulmonary disease (COPD), as well as to compare patients with individuals from the general population and to test if pulmonary rehabilitation can reduce fatigue and functional limitations, and thus improve health. A further aim was to test the Fatigue Impact Scale (FIS) among patients with COPD. Two studies (I, II) had a descriptive comparative design with data from 36 and 151 patients with COPD respectively, and 37 and 95 individuals respectively, randomly selected from the general population. One study (III) was a randomised pre-test post-test study with 12 patients with COPD randomised to 12 weeks’ pulmonary rehabilitation and 14 patients in a control group. In a further study (IV), the FIS was tested for validity and reliability among 296 patients with COPD who reported fatigue. Assessments: Structured questions frequency, duration and severity of fatigue, functional limitations due to fatigue with FIS, six minutes’ walking distance, hand grip strength, functional performance and satisfaction with Canadian Occupational Performance Measure and health with St George’s Hospital Respiratory Questionnaire and Short Form-36. Almost half of the patients with COPD had a problem with fatigue every day and experienced fatigue as a severe symptom. More than 44% reported that fatigue was one of the worst symptoms. The experience of fatigue was related to the patients’ functional performance and health perceptions. Patients with COPD experienced a higher frequency, longer daily duration and greater severity of fatigue than individuals from the general population. After a 12 week pulmonary rehabilitation programme, there were no statistically significant differences between the patients randomised to the rehabilitation group and those in the control group. The patients in the rehabilitation group improved walking distances, performance and satisfaction with regard to their own selected activities compared with baseline. Confirmatory factor analysis on the three-factor model proposed for FIS showed that the fit of the model was not acceptable. Further validation of the FIS resulted in a removal of 15 items (FIS-25) and support for Pipers´ theoretical framework of subjective manifestations of fatigue including physical, emotional and cognitive dimensions and a general behavioural factor. The internal consistency, sensitivity and stability correlations of FIS-25 were satisfactory. In conclusion, fatigue is a major concern among patients with COPD, impacting on functioning and health. Interventions with 12 weeks’ pulmonary rehabilitation might not be effective enough to reduce fatigue and the functional limitations due to fatigue. More research is needed to solve the symptom burden of fatigue and its impact on functioning and health in patients with COPD.

The purpose of the study was threefold: (1) to determine the factor structure of mathematical thinking at the within-classroom and at the between-classroom level / (2) to investigate the extent of variation in the relationships among different mathematical thinking constructs at the within- and between-classroom levels / and (3) to examine the cross-level interactions among different types of mathematical thinking. Previous research was extended by investigating the factor structure of mathematical thinking in derivative at the within- and between-classroom levels, and further examining the direct, indirect, and cross-level relations among different types of mathematical thinking. Multilevel analyses of a cross-sectional dataset containing two independent samples of undergraduate students nested within classrooms showed that the within-structure of mathematical thinking includes enactive, iconic, algorithmic, algebraic, formal, and axiomatic thinking, whereas the between-structure contains formal-axiomatic, proceptual-symbolic, and conceptual-embodied thinking. Major findings from the two-level mathematical thinking model revealed that: (1) enactive, iconic, algebraic, and axiomatic thinking varied primarily as a function of formal and algorithmic thinking / (2) the strongest direct effect of formal-axiomatic thinking was on proceptual-symbolic thinking / (3) the nature of the relationships was cyclic at the between-classroom level / (4) the within-classroom mathematical thinking constructs significantly moderate the relationships among conceptual-embodied, proceptual-symbolic, and formal-axiomatic thinking / and (5) the between-classroom mathematical thinking constructs moderate the relationships among enactive, iconic, algorithmic, algebraic, formal, and axiomatic thinking. The challenges when using multilevel exploratory factor analysis, multilevel confirmatory factor analysis, and multilevel structural equation modeling with categorical variables are emphasized. Methodological and educational implications of findings are discussed.