Browsing by Subject "Structural Equation Modeling"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item Comparing Model-based and Design-based Structural Equation Modeling Approaches in Analyzing Complex Survey Data(2011-10-21) Wu, Jiun-YuConventional statistical methods assuming data sampled under simple random sampling are inadequate for use on complex survey data with a multilevel structure and non-independent observations. In structural equation modeling (SEM) framework, a researcher can either use the ad-hoc robust sandwich standard error estimators to correct the standard error estimates (Design-based approach) or perform multilevel analysis to model the multilevel data structure (Model-based approach) to analyze dependent data. In a cross-sectional setting, the first study aims to examine the differences between the design-based single-level confirmatory factor analysis (CFA) and the model-based multilevel CFA for model fit test statistics/fit indices, and estimates of the fixed and random effects with corresponding statistical inference when analyzing multilevel data. Several design factors were considered, including: cluster number, cluster size, intra-class correlation, and the structure equality of the between-/within-level models. The performance of a maximum modeling strategy with the saturated higher-level and true lower-level model was also examined. Simulation study showed that the design-based approach provided adequate results only under equal between/within structures. However, in the unequal between/within structure scenarios, the design-based approach produced biased fixed and random effect estimates. Maximum modeling generated consistent and unbiased within-level model parameter estimates across three different scenarios. Multilevel latent growth curve modeling (MLGCM) is a versatile tool to analyze the repeated measure sampled from a multi-stage sampling. However, researchers often adopt latent growth curve models (LGCM) without considering the multilevel structure. This second study examined the influences of different model specifications on the model fit test statistics/fit indices, between/within-level regression coefficient and random effect estimates and mean structures. Simulation suggested that design-based MLGCM incorporating the higher-level covariates produces consistent parameter estimates and statistical inferences comparable to those from the model-based MLGCM and maintain adequate statistical power even with small cluster number.Item From Substitution to Coping: Developing and Testing a Leisure Constraints-Based Coping Model(2010-01-14) Tseng, Yung-PingThe conceptualization of leisure constraints is dependent on negotiating a hierarchy of intrapersonal, interpersonal, and structural leisure constraints. It has become a recognizable and distinct subfield within leisure studies. Research has shown that the leisure constraints should not be necessarily viewed as insurmountable obstacles. Individuals can negotiate constraints by applying an array of coping mechanisms. Recently, Iwasaki and Schneider (2003) and Schneider and Stanis (2007) proposed that constraints negotiation and coping with stress share much in common. Leisure constraints are considered elements of stress, whereas constraint negotiation appears to share commonalities with ways of coping with stress. The distinction between negotiation and coping is that negotiation is something people have engaged in prior to participating in the activity, whereas coping involves strategies people more typically engage in during active participation (in response to unwanted or unanticipated situations). Based on past literature, I constructed a constraints-coping model to extend our understanding of constraints negotiation by integrating an understanding of coping mechanisms into leisure constraints-negotiation models. In order to broaden the scope of a constraints-coping framework, I integrated additional social indicators (e.g., commitment, motivation, place attachment, and frequency of participation) into my hypothesized model. First, my testing of the constraints-coping model provided empirical support for Iwasaki and his colleagues' suggestion that coping strategies can be potentially integrated into models of constraints-negotiation processes. Second, I confirmed that the three types of onsite constraints continue to have relevance for active participants. The three types of constraining factors directly influence subsequent aspects of leisure engagement for recreationists already participating. Third, I confirmed that recreationists are more likely to cope with constraints by employing an array of problem-focused coping strategies, rather than to simply adjust cognitively. However, my findings illustrate that recreationists' coping responses vary in response to different types of constraints encountered (e.g., intrapersonal, interpersonal, and structural). The experience of constraints did not universally result in the increased use of coping. Fourth, my results confirm that motivation is an immediate antecedent of constraints as well as a potential trigger for encouraging more problem-focused coping strategies. Last, four selected key variables (e.g., place attachment, commitment motivation, and frequency of participation) demonstrated different effects on influencing active participants' perceived constraints and subsequent coping strategies. Future investigations of coping strategies should continue to explore how active participants cope with onsite constraints based on a constraints-coping model in different settings.Item Impact of Not Fully Addressing Cross-Classified Multilevel Structure in Testing Measurement Invariance and Conducting Multilevel Mixture Modeling within Structural Equation Modeling Framework(2014-07-25) Im, MyungIn educational settings, researchers are likely to encounter multilevel data without strictly nested or hierarchical but cross-classified multilevel structure. However, due to the lack of familiarity and limitations of statistical software with cross-classified model, most substantive researchers adopt then the less optimal approaches to analyze cross-classified multilevel data. Two separate Monte Carlo studies were conducted to evaluate the impacts of misspecifying cross-classified structure data as hierarchical structure data in two different analytical settings under the structural equation modeling (SEM) framework. Study 1 evaluated the performance of conventional multilevel confirmatory factor analysis (MCFA) which assumes hierarchical multilevel data in testing measurement invariance, especially when the noninvariance exists at the between-level groups. We considered two design factors, intra-class correlation (ICC) and magnitude of factor loading differences. This simulation study showed low empirical power in detecting noninvariance under low ICC conditions. Furthermore, the low power was plausibly related to the underestimated ICC and the underestimated factor loading differences due to the redistribution of the variance component from the crossed factor ignored in the analysis. Study 2 examined the performance of conventional multilevel mixture models (MMMs), which assume hierarchical multilevel data, on the classification accuracy of class enumeration and individuals? class assignment when the latent class variable is at the between (cluster)-level. We considered a set of study conditions, including cluster size, degree of partial cross-classification, and mixing proportion of subgroups. From the results of the study, ignoring a crossed factor caused overestimation of the variance component of the remaining crossed factor at the between-level which was redistributed from the ignored crossed factor in the analysis. Moreover, no SEM statistical program can conduct MMM and take into account of the cross-classified data structure simultaneously. Hence, a researcher should acknowledge this limitation and be cautioned when conventional MMM is utilized with cross-classified multilevel data given the inflated variance component associated with the remaining crossed factor. Implications of the findings and limitations for each study are discussed.Item Modeling the relationships among topical knowledge, anxiety, and integrated speaking test performance: a structural equation modeling approach(2010-05) Huang, Heng-Tsung Danny; Plakans, Lia; Horwitz, Elaine Kolker, 1950-; Schallert, Diane L.; Garza, Thomas J.; Vaughn, Brandon K.Thus far, few research studies have examined the practice of integrated speaking test tasks in the field of second/foreign language oral assessment. This dissertation utilized structural equation modeling (SEM) and qualitative techniques to explore the relationships among topical knowledge, anxiety, and integrated speaking test performance and to compare the influence of topical knowledge and anxiety, respectively, on independent speaking test performance and integrated speaking test performance. Three instruments were employed in this study. First, three integrated tasks were derived from TOEFL-iBT preparation materials, and three independent tasks were developed specifically for this research study. Second, four topical knowledge tests (TKTs) were constructed by six content experts and validated on a group of 421 Taiwanese EFL learners. Third, the state anxiety inventory (SAI) from the State-Trait Anxiety Inventory was adopted. A total of 352 Taiwanese EFL students were recruited for the official study. At the first stage, they filled out the personal information sheet and responded to the TKTs. At the second stage, they took two independent tasks for which they spoke without input support, responded to an SAI, performed two integrated tasks in which they orally summarized the textual and auditory input given to them, and completed another SAI. Finally, 23 volunteers took part in follow-up interviews. The quantitative data were analyzed using the two-step SEM approach and the interview data were examined using a series of qualitative techniques, leading to five primary findings. First, topical knowledge and anxiety both strongly influenced the integrated speaking performance, though in an opposite manner. Second, topical knowledge did not significantly affect anxiety. Third, the effect of topical knowledge on independent speaking performance and integrated speaking performance varied depending on the topics of the tasks. Fourth, the impact of anxiety on independent speaking performance and integrated speaking performance also differed according to the topics of the tasks. Fifth, participants were overwhelmingly positive about the integrated tasks. In light of the findings, several implications are proposed for second/foreign language oral assessment theory, research methodology, and practice.Item Second Level Cluster Dependencies: A Comparison of Modeling Software and Missing Data Techniques(2011-10-21) Larsen, Ross Allen AndrewDependencies in multilevel models at the second level have never been thoroughly examined. For certain designs first-level subjects are independent over time, but the second level subjects may exhibit nonzero covariances over time. Following a review of revelant literature the first study investigated which widely used computer programs adequately take into account these dependencies in their analysis. This was accomplished through a simulation study with SAS, and examples of analyses with Mplus and LISREL. The second study investigated the impact of two different missing data techniques for such designs in the case where data is missing at the first level with a simulation study in SAS. The first study simulated data produced in a multiyear study varying the numbers of subjects in the first and second levels, the number of data waves, the magnitude of effects at both the first and second level, and the magnitude of the second level covariance. Results showed that SAS and the MULTILEV component in LISREL analyze such data well while Mplus does not. The second study compared two missing data techniques in the presence of a second level dependency, multiple imputation (MI) and full information maximum likelihood (FIML). They were compared in a SAS simulation study in which the data was simulated with all the factors of the first study and the addition of missing data varied in amounts and patterns (missing completely at random or missing at random). Results showed that FIML is superior to MI because it produces lower bias and correctly estimates standard errorsItem Testing the Effectiveness of Various Commonly Used Fit Indices for Detecting Misspecifications in Multilevel Structure Equation Models(2011-02-22) Hsu, Hsien-YuanTwo Monte Carlo studies were conducted to investigate the sensitivity of fit indices in detecting model misspecification in multilevel structural equation models (MSEM) with normally distributed or dichotomous outcome variables separately under various conditions. Simulation results showed that RMSEA and CFI only reflected within-model fit. In addition, SRMR for within-model (SRMR-W) was more sensitive to within-model misspecifications in factor covariances than pattern coefficients regardless of the impact of other design factors. Researchers should use SRMR-W in combination with RMSEA and CFI to evaluate the within-mode. On the other hand, SRMR for between-model (SRMR-B) was less likely to detect between-model misspecifications when ICC decreased. Lastly, the performance of WRMR was dominated by the misfit of within-model. In addition, WRMR was less likely to detect the misspecified between-models when ICC was relative low. Therefore, WRMR can be used to evaluate the between-model fit when the within-models were correctly specified and the ICC was not too small.Item The Role of Acculturation, Ethnic Identity, and Religious Fatalism on Attitudes Towards Seeking Psychological Help Among Coptic Americans.(2012-07-16) Boulos, Sallie AnnThe purpose of this current study was to determine the role of acculturation, ethnic identity, and religious fatalism regarding attitudes towards seeking psychological help among Coptic (Egyptian Christian) Americans. In addition, differences between groups of gender and generational status, first-generation adult immigrants versus U.S.-born second-generation Copts, were analyzed. The study had a total sample of 91 individuals that self-identified as Coptic by race and/or Coptic Orthodox by religion, who voluntarily completed an anonymous online questionnaire. Results indicate that ethnic identity and acculturation are strong predictors of religious fatalistic beliefs, and those who identified as having more Arab ethnic identity and less assimilation to dominate culture have stronger religious fatalistic beliefs than those who identified with more western culture and an American ethnic identity. However, religious fatalism and ethnic identity were not significant predictors of attitudes towards seeking psychological help, and other variables such as stigma, language barriers, and skepticism of western psychology may be better predictors of attitudes towards seeking psychological help. Between groups comparisons identified subtle differences between males and females, and between first and second-generation Coptic Americans on acculturation, ethnic identity, and religious fatalism, but the groups were not statistically significant from one another. Clinical implications and directions for future research will also be discussed.