Browsing by Subject "Factor analysis"
Now showing 1 - 10 of 10
Results Per Page
Sort Options
Item Evaluation of single- and multilevel factor mixture model estimation(2007-05) Allua, Shane Suzanne, 1975-; Beretvas, Susan NatashaConfirmatory factor analysis (CFA) models test the plausibility of latent constructs hypothesized to account for relations among observed variables. CFA models can be used to model both hierarchical data structures as a result of cluster sampling designs and investigate the plausibility of latent classes or unobserved classes of individuals. Recent research has suggested preliminary evidence on the accuracy of typical fit indices (AIC, BIC, aBIC, LMR aLRT) among various single-level latent class models, multilevel latent class models that correct for biased standard error estimates as a result of nested data, and growth mixture models (Clark & Muthén, 2007; Nylund et al., 2006, Tofighi & Enders, 2006). But few, if any, researchers have studied the accuracy of the fit indices in multilevel factor mixture models. The purpose of this study was to extend the literature in this less researched area and assess the performance of typical fit indices used to compare factor mixture models. Class separation, intraclass correlation, and between-cluster sample size were manipulated to emulate realistic typical research conditions. The proportion of times out of a possible 100 replications in which each of the AIC, BIC, aBIC, and LMR aLRT led to selection of the correctly specified model among other mis-specified models was recorded. Results for data generated to fit one-class models indicated that the BIC and aBIC outperformed the AIC and the LMR aLRT was nonsignificant nearly 100% of the time, supporting the correct one-class model. Performance of all fit indices was, however, poor when data were generated to originate from two-class models. The AIC and LMR aLRT tended to perform better than the BIC and aBIC, although accuracy of all fit indices increased as a function of increasing class separation and between-cluster sample size. Implications and recommendations regarding optimal fit indices under various conditions are reported. It is hoped that the current research has provided initial evidence of conditions in which the various fit indices are more likely to model the correct number of latent classes in multilevel data.Item Evaluation of single- and multilevel factor mixture model estimation(2007) Allua, Shane Suzanne; Beretvas, Susan NatashaItem Exploring the Underlying Factor Structure of the Home Literacy Environment (HLE) in a Spanish Translation of the Familia Inventory(2014-06-02) Adame-Hernandez, CindyDifferences in children?s skills at the beginning of formal schooling have been reported, with Hispanic children, often performing below their Caucasian counterparts. The home literacy environment (HLE) has been reported to be the cause of the early differences, but the paucity of Spanish language instruments aimed at studying the HLE of Hispanic families has affected research in this important area. One available instrument is the Spanish version of the Familia Inventory, designed to assess family interactions related to literacy. Research has shown that the Spanish inventory is not equivalent to the original English version possibly due to an erroneous translation. The purpose of this study is to complete a psychometric examination of a re-translated Spanish language version of the Familia Inventory with a low-socioeconomic Spanish-speaking Hispanic sample using confirmatory (CFA) and exploratory factor analysis (EFA). The inventory was administered to 132 parents of preschoolers. Results from CFA models revealed that the 10 a-priori subscales suggested by the developer of the inventory and a four-factor model suggested by a researcher did not yield adequate model fit with this sample. Follow-up analyses of individual subscales yielded poor fit for the majority of the subscales. Exploratory factor analysis using the original 57 items of the inventory suggested a five-factor model accounting for 43.3% of the variance. It is suggested that the inventory needs to be theoretically re-conceptualized.Item Factor analysis as a data compression technique(Texas Tech University, 1973-08) Pore, Michael DavidNot availableItem On Eckford Cohen's direct factor sets(Texas Tech University, 1965-05) McWilliams, Gerald VernonNot availableItem Quality in linguistic metaphors(Texas Tech University, 1987-05) Williams, Patrick SwinnyNot availableItem A quantitative study : administrative leaders' perceptions of succession planning and management practices within community colleges(2012-05) Coward, Leslie Anne Wright; Gooden, Mark A.; Roueche, John E.; Vasquez Heilig, Julian; Butler, Johnny S.; Roueche, Suanne D.; Bumphus, AileenThe purpose of this quantitative study was to examine the perceptions of senior administrative and middle manager community college leaders regarding current succession planning and management practices occurring within their institutions. Three research questions guided this study: (1) Is the four succession planning and management components structurally related, (2) Is there a difference in how senior administrative and middle manager leaders evaluate succession planning and management components, and (3) Is there a difference between size and location of institution in regards to status of succession planning and management components? A suitable succession planning and management instrument was not found; therefore, the Wright-Coward Succession Planning and Management Survey (WCSPMS) instrument was developed. An exploratory factor analysis was used to address research question one and test the structural relationship of the common succession planning and management components of the survey. A second statistical procedure, multivariate analysis of variance, was used to analyze differences between the four dependent measures of succession planning and management and leadership level, and institutional factors. Findings from this study suggested (1) items on the WCSPMS instrument are correlated and three relatively independent succession planning and management factors are associated with the 20 underlying items, and (2) there is a statistical significant difference between leadership level in regards to perceptions of succession planning and management practices. Furthermore, this study indicated there is much work to be done by community college leaders in the area of succession planning and management.Item Scale development and construct validation of a chimpanzee rating scale(2010-08) Freeman, Hani; Gosling, Sam; Josephs, Robert A.; Beevers, Christopher G.; Lewis, Rebecca J.; Nehete, PramodThe last two decades have seen a surge in published research on primate personality. This surge contrasts with the paucity of research over the preceding century. People interested in primate personality research come from a broad range of fields, but they are all interested in measuring primate personality in a way that is reliable, valid, and practical. This dissertation aims to describe the development and evaluation of the construct validity of a new rating scale in chimpanzees. The scale is based on a bottom-up approach to scale development and was developed using steps from both Uher (2008a,b) and Gosling (1998). As described in Chapter 3, the scale was evaluated by using it to rate 143 chimpanzees at the University of Texas MD Anderson Cancer Center Facility in Bastrop, TX. Twenty-one people who have worked with the chimpanzees between 6 months to 20 years rated the chimpanzees. Chapter 4 describes how inter-class correlation coefficients (ICCs) were used to calculate the reliability of the items on the scale. There was only one item (predictable) that turned out to not be reliable. The other 40 items were included in subsequent analyses. An exploratory factor analysis, as described in Chapter 5, was performed in order to determine the structure underlying the scale. Five methods were used to determine that a six-factor solution fit the data best. The six factors were labeled Reactivity, Dominance, Openness, Extroversion Agreeableness, and Conscientiousness based on the degree to that they correlated with other previous chimpanzees scales that used those labels. The convergent and discriminant validity of the factors was evaluated, as described in Chapter 6, by looking at the predicted relationships between each of the six factors and the variables of sex, age, rearing history, behavior in reaction to a novel stimulus, general behavior, injuries, illnesses, blood chemistry, and cortisol. The results indicate that there is a lack of evidence for convergent validity, but some evidence for discriminant validity of the new chimpanzee rating scale. The discussion in Chapter 7 focuses on the findings from the study as well as strengths and limitations of the new chimpanzee rating scale.Item Unbiased F-tests for factorial experiments with correlated data(Texas Tech University, 1981-08) Pavur, Robert JamesNot availableItem The use of factor mixture modeling to investigate population heterogeneity in hierarchical models of intelligence(2008-08) Reynolds, Matthew Robert; Beretvas, Susan Natasha; Keith, Timothy, 1952-Spearman’s law of diminishing returns (SLODR) posits that at higher levels of general cognitive ability, the general factor (g) performs less well in explaining individual differences in cognitive test performance. The present study used factor mixture modeling to investigate SLODR in the Kaufman Assessment Battery for Children--Second Edition (KABC-II). Factor mixture modeling was a useful method to study SLODR because group membership was determined based on probabilities derived from the model. A second-order confirmatory factor model, consistent with three-stratum theory (Carroll, 1993), was modeled as a within-class factor structure. The fit of several models with varying number of classes and factorial invariance restrictions were compared. A sex covariate was also included with the models that provided the best fit for the data. The results indicated that a two-class model, which allowed for g mean differences, and class-specific g variances and subtest residual variances, provided the most parsimonious explanation of the data. Consistent with SLODR, the second-order general factor explained less subtest variance and less variance in the first-order factors for those of higher general ability. The standardized subtest residual variances were also larger in the high ability class than in the low ability class. Controlling for g, boys performed higher than girls in visual-spatial ability in each of the low and high ability classes. The findings from this study have implications for future research on the interpretation of intelligence test scores across the ability distribution.