Search Constraints
« Previous |
1 - 10 of 13
|
Next »
Search Results
- Creator:
- Holsonbake, Cheryl Ann
- Description:
- Public institutions of all kinds are being subjected to more accountability by legislators, educators, the media, and taxpayers. But, U.S. colleges and universities that once enjoyed relative freedom from accountability have been increasingly in the spotlight. In light of the recent nationwide recession and painfully slow recovery, college graduation rates are being heavily scrutinized, especially among public community colleges and universities.
This study focused on graduates of Kern High School District who enrolled at CSU Bakersfield as first-time freshmen and whether taking advanced mathematics courses improved their odds of completing a college diploma. Binary logistical regression results indicated an overall model including the rigor of students’ last high school mathematics class was reliable in distinguishing between those who graduated with a bachelor’s degree and those who did not. Holding all other variables constant, KHSD students taking any course(s) above Algebra 2 were
3.2 times more likely to complete college in four years. The findings held for five-and six-year college graduation rates as well. Students taking more rigorous mathematics courses were 2.2 times more likely to finish their degree in five years and 1.8 times more likely to finish their degree in six years.
- Resource Type:
- Masters Thesis
- Campus Tesim:
- Bakersfield
- Department:
- Public Policy and Administration
- Creator:
- Caldwell, Linda L., Xie, Hui, Wegner, Lisa, Smith, Edward A., and Weybright, Elizabeth H.
- Description:
- Education is one of the strongest predictors of health worldwide. In South Africa, school dropout is a crisis where by Grade 12, only 52% of the age appropriate population remain enrolled. Survival analysis was used to identify the risk of dropping out of secondary school for male and female adolescents and examine the influence of substance use and leisure experience predictors while controlling for demographic and known predictors using secondary, longitudinal data. Results indicated being male, not living with one's mother, smoking cigarettes in the past month, and lower levels of leisure-related intrinsic motivation significantly predicted dropout. Results support comprehensive prevention programmes that target risk behaviour and leisure.
- Resource Type:
- Article
- Identifier:
- 0256-0100
- Campus Tesim:
- Northridge
- Creator:
- Heese, Holland R.
- Description:
- Restoration of fire-excluded pine ecosystems is a major conservation and management goal. Land managers have used prescribed fires to reduce accumulated forest floor fuels and restore pinelands. While these fires have been successful at reducing fuels, tree mortality in these restoration fires can be as high as 75 to 95 percent. In this study, I model post-fire mortality of longleaf pine (in two stands in the Mountain Longleaf National Wildlife Refuge in northeastern Alabama) using logistic models composed of only predictors that can be measured pre-fire. These methods are extended by the addition of spatial competition functions since such measures are drawn from available data for managers, and have been shown to have effects on growth and mortality. The best models, selected by AIC, predict survival as well or better than earlier models but have high false mortality predictions. The spatial dynamics of the stand are also studied pre-fire and post-fire to determine the effect of prescribed fire and inter-tree competition. Post-fire, spatial distribution of the trees did not significantly change. Earlier studies detected differences in the spatial dynamics between different classes of longleaf pine. These dynamics were confirmed in some results and in others questioned. Small trees (DBH < 30 cm) clustered away from large trees (DBH > 30 cm). Large trees were more dispersed than a random process (Poisson) would dictate. Juveniles (DBH < 5 cm) were shown to cluster away from large trees, but aggregate around other small trees.
- Resource Type:
- Masters Thesis
- Campus Tesim:
- Humboldt
- Department:
- Mathematical Modeling
- Creator:
- Frane, Andrew Vann
- Description:
- Simulations were conducted to evaluate the statistical power and Type I error control provided by several multiple-comparisons procedures in two-group designs. Stepwise Bonferroni-based procedures, which are known to control the familywise Type I error rate, tended to be more powerful than other methods but did not control the per-family Type I error rate (PFER). It is proposed that more attention should be given to the PFER, particularly with regard to these procedures. Only two methods controlled the PFER: the classical Bonferroni procedure and a modified version of MANOVA-protection. Which of these two procedures was more powerful depended on multiple factors that this paper describes in detail. It is concluded that which multiple-comparisons procedure is preferable depends on the number of outcome variables, the importance of the PFER, the necessity of confidence intervals, and the extent to which significance in multiple variables is more valuable than significance in one variable.
- Resource Type:
- Thesis
- Campus Tesim:
- Los Angeles
- Department:
- Psychology
- Creator:
- Kroening, Jonathan
- Description:
- The segmentation of survey respondents into actionable groups is a familiar analysis performed in market research. Identifying unique subsets of consumers informs better decision-making in a given product space. Standard practice in the industry is to employ k-Means and Hierarchical Clustering Analysis methods, and in some cases ensembles thereof, to find these segments. It is commonly recognized that clustering as a problem is ill-defined. The absence of a response variable or labels in the data means unsupervised learning methods are difficult to evaluate. Furthermore, cluster analysis will always produce a clustering solution whether or not there are underlying relationships in the data to justify those clusters. As there is no ground-truth, accuracy measure, or error signal with which to measure a solution, it is difficult for a market researcher to know if a segmentation has utility. Beyond utility, segmentations become about the story that can be told by a particular clustering of the respondents. This thesis considers a variety of ways segmentations can be appraised objectively and how doing so impacts the story a market researcher can draw from the data. It will define criteria with which to evaluate the output of clustering methods. The criteria will measure a segmentation’s usefulness to domain experts as representative of an actionable marketplace. Consequently, an array of methods and distance measures will also be analyzed and evaluated across these evaluation criteria to identify best-practice algorithms and dissimilarity measures for market research cluster analyses. Five public datasets are used in this study and consist of respondent-level survey data on Likert scale variables.
- Resource Type:
- Thesis
- Campus Tesim:
- Los Angeles
- Department:
- Interdisciplinary Studies
- Creator:
- Park, Jonathan
- Description:
- Dynamic systems (e.g., families, student-teacher, etc.) present themselves as a powerful means of assessing multiple informants and how they interact with each other across a given period of time. the current study sought to propose a novel statistical methodology for the simultaneous linking of tests across both informants and time. This was accomplished through the application of multi-test parameter linking under Item Response Theory. Data were taken from the Fullerton Longitudinal Study and assessed the construct of Positive Family Relationships (PFR)—a measure of how well family members get along and support each other—and assessed mothers and children from 9- to 17-years of age. the procedures yielded theta (&thetas;) scores which represent equated scores of mother- and child-reported PFR. the &thetas;s were found to be highly correlated with the original summed scores. Furthermore, discrepancies between the summed scores and the ?s are likely the result of the removal of measurement error associated with developmental and/or interpretational differences amongst the measures. the methods presented in this paper allow researchers to confidently apply survey-based data to the assessment of dynamic systems.
- Resource Type:
- Masters Thesis
- Campus Tesim:
- Fullerton
- Department:
- Department of Psychology
- Creator:
- Delarosa, Beverly
- Description:
- An Analysis for 24 Cancers in 30 Countries in 2012: Incidence Rates and Treatment Effectiveness
Beverly Delarosa
Statistics
2016-05
- Resource Type:
- Project
- Campus Tesim:
- Long Beach