Matching Items (3)
Filtering by
- All Subjects: Structural equation modeling
- Creators: Cham, Hei Ning
- Creators: Baker, Dale R.
- Member of: ASU Electronic Theses and Dissertations
Description
Random Forests is a statistical learning method which has been proposed for propensity score estimation models that involve complex interactions, nonlinear relationships, or both of the covariates. In this dissertation I conducted a simulation study to examine the effects of three Random Forests model specifications in propensity score analysis. The results suggested that, depending on the nature of data, optimal specification of (1) decision rules to select the covariate and its split value in a Classification Tree, (2) the number of covariates randomly sampled for selection, and (3) methods of estimating Random Forests propensity scores could potentially produce an unbiased average treatment effect estimate after propensity scores weighting by the odds adjustment. Compared to the logistic regression estimation model using the true propensity score model, Random Forests had an additional advantage in producing unbiased estimated standard error and correct statistical inference of the average treatment effect. The relationship between the balance on the covariates' means and the bias of average treatment effect estimate was examined both within and between conditions of the simulation. Within conditions, across repeated samples there was no noticeable correlation between the covariates' mean differences and the magnitude of bias of average treatment effect estimate for the covariates that were imbalanced before adjustment. Between conditions, small mean differences of covariates after propensity score adjustment were not sensitive enough to identify the optimal Random Forests model specification for propensity score analysis.
ContributorsCham, Hei Ning (Author) / Tein, Jenn-Yun (Thesis advisor) / Enders, Stephen G (Thesis advisor) / Enders, Craig K. (Committee member) / Mackinnon, David P (Committee member) / Arizona State University (Publisher)
Created2013
Description
Science, Technology, Engineering & Mathematics (STEM) careers have been touted as critical to the success of our nation and also provide important opportunities for access and equity of underrepresented minorities (URM's). Community colleges serve a diverse population and a large number of undergraduates currently enrolled in college, they are well situated to help address the increasing STEM workforce demands. Geoscience is a discipline that draws great interest, but has very low representation of URM's as majors. What factors influence a student's decision to major in the geosciences and are community college students different from research universities in what factors influence these decisions? Through a survey-design mixed with classroom observations, structural equation model was employed to predict a student's intent to persist in introductory geology based on student expectancy for success in their geology class, math self-concept, and interest in the content. A measure of classroom pedagogy was also used to determine if instructor played a role in predicting student intent to persist. The targeted population was introductory geology students participating in the Geoscience Affective Research NETwork (GARNET) project, a national sampling of students in enrolled in introductory geology courses. Results from SEM analysis indicated that interest was the primary predictor in a students intent to persist in the geosciences for both community college and research university students. In addition, self-efficacy appeared to be mediated by interest within these models. Classroom pedagogy impacted how much interest was needed to predict intent to persist, in which as classrooms became more student centered, less interest was required to predict intent to persist. Lastly, math self-concept did not predict student intent to persist in the geosciences, however, it did share variance with self-efficacy and control of learning beliefs, indicating it may play a moderating effect on student interest and self-efficacy. Implications of this work are that while community college students and research university students are different in demographics and content preparation, student-centered instruction continues to be the best way to support student's interest in the sciences. Future work includes examining how math self-concept may play a role in longitudinal persistence in the geosciences.
ContributorsKraft, Katrien J. van der Hoeven (Author) / Husman, Jenefer (Thesis advisor) / Semken, Steven (Thesis advisor) / Baker, Dale R. (Committee member) / McConnell, David (Committee member) / Arizona State University (Publisher)
Created2014
Description
For this thesis a Monte Carlo simulation was conducted to investigate the robustness of three latent interaction modeling approaches (constrained product indicator, generalized appended product indicator (GAPI), and latent moderated structural equations (LMS)) under high degrees of nonnormality of the exogenous indicators, which have not been investigated in previous literature. Results showed that the constrained product indicator and LMS approaches yielded biased estimates of the interaction effect when the exogenous indicators were highly nonnormal. When the violation of nonnormality was not severe (symmetric with excess kurtosis < 1), the LMS approach with ML estimation yielded the most precise latent interaction effect estimates. The LMS approach with ML estimation also had the highest statistical power among the three approaches, given that the actual Type-I error rates of the Wald and likelihood ratio test of interaction effect were acceptable. In highly nonnormal conditions, only the GAPI approach with ML estimation yielded unbiased latent interaction effect estimates, with an acceptable actual Type-I error rate of both the Wald test and likelihood ratio test of interaction effect. No support for the use of the Satorra-Bentler or Yuan-Bentler ML corrections was found across all three methods.
ContributorsCham, Hei Ning (Author) / West, Stephen G. (Thesis advisor) / Aiken, Leona S. (Committee member) / Enders, Craig K. (Committee member) / Arizona State University (Publisher)
Created2010