Matching Items (32)
Description
This work presents two complementary studies that propose heuristic methods to capture characteristics of data using the ensemble learning method of random forest. The first study is motivated by the problem in education of determining teacher effectiveness in student achievement. Value-added models (VAMs), constructed as linear mixed models, use students’ test scores as outcome variables and teachers’ contributions as random effects to ascribe changes in student performance to the teachers who have taught them. The VAMs teacher score is the empirical best linear unbiased predictor (EBLUP). This approach is limited by the adequacy of the assumed model specification with respect to the unknown underlying model. In that regard, this study proposes alternative ways to rank teacher effects that are not dependent on a given model by introducing two variable importance measures (VIMs), the node-proportion and the covariate-proportion. These VIMs are novel because they take into account the final configuration of the terminal nodes in the constitutive trees in a random forest. In a simulation study, under a variety of conditions, true rankings of teacher effects are compared with estimated rankings obtained using three sources: the newly proposed VIMs, existing VIMs, and EBLUPs from the assumed linear model specification. The newly proposed VIMs outperform all others in various scenarios where the model was misspecified. The second study develops two novel interaction measures. These measures could be used within but are not restricted to the VAM framework. The distribution-based measure is constructed to identify interactions in a general setting where a model specification is not assumed in advance. In turn, the mean-based measure is built to estimate interactions when the model specification is assumed to be linear. Both measures are unique in their construction; they take into account not only the outcome values, but also the internal structure of the trees in a random forest. In a separate simulation study, under a variety of conditions, the proposed measures are found to identify and estimate second-order interactions.
ContributorsValdivia, Arturo (Author) / Eubank, Randall (Thesis advisor) / Young, Dennis (Committee member) / Reiser, Mark R. (Committee member) / Kao, Ming-Hung (Committee member) / Broatch, Jennifer (Committee member) / Arizona State University (Publisher)
Created2013
Description
The purpose of this study was to compare perceptions of success and failure, attributions of success and failure, predictions of future success, and reports of out-of-class engagement in composition among middle school band students composing in open task conditions (n = 32) and closed task conditions (n = 31). Two intact band classes at the same middle school were randomly assigned to treatment groups. Both treatment groups composed music once a week for eight weeks during their regular band time. In Treatment A (n = 32), the open task group, students were told to compose music however they wished. In Treatment B (n = 31), the closed task group, students were given specific, structured composition assignments to complete each week. At the end of each session, students were asked to complete a Composing Diary in which they reported what they did each week. Their responses were coded for evidence of perceptions of success and failure as well as out-of-class engagement in composing. At the end of eight weeks, students were given three additional measures: the Music Attributions Survey to measure attributions of success and failure on 11 different subscales; the Future Success survey to measure students' predictions of future success; and the Out-of-Class Engagement Letter to measure students' engagement with composition outside of the classroom. Results indicated that students in the open task group and students in the closed task group behaved similarly. There were no significant differences between treatment groups in terms of perceptions of success or failure as composers, predictions of future success composing music, and reports of out-of-class engagement in composition. Students who felt they failed at composing made similar attributions for their failure in both treatment groups. Students who felt they succeeded also made similar attributions for their success in both treatment groups, with one exception. Successful students in the closed task group rated Peer Influence significantly higher than the successful students in the open task group. The findings of this study suggest that understanding individual student's attributions and offering a variety of composing tasks as part of music curricula may help educators meet students' needs.
ContributorsSchwartz, Emily, 1985- (Author) / Stauffer, Sandra L (Thesis advisor) / Tobias, Evan (Committee member) / Schmidt, Margaret (Committee member) / Broatch, Jennifer (Committee member) / Sullivan, Jill (Committee member) / Arizona State University (Publisher)
Created2014
Description
Obtaining high-quality experimental designs to optimize statistical efficiency and data quality is quite challenging for functional magnetic resonance imaging (fMRI). The primary fMRI design issue is on the selection of the best sequence of stimuli based on a statistically meaningful optimality criterion. Some previous studies have provided some guidance and powerful computational tools for obtaining good fMRI designs. However, these results are mainly for basic experimental settings with simple statistical models. In this work, a type of modern fMRI experiments is considered, in which the design matrix of the statistical model depends not only on the selected design, but also on the experimental subject's probabilistic behavior during the experiment. The design matrix is thus uncertain at the design stage, making it diffcult to select good designs. By taking this uncertainty into account, a very efficient approach for obtaining high-quality fMRI designs is developed in this study. The proposed approach is built upon an analytical result, and an efficient computer algorithm. It is shown through case studies that the proposed approach can outperform an existing method in terms of computing time, and the quality of the obtained designs.
ContributorsZhou, Lin (Author) / Kao, Ming-Hung (Thesis advisor) / Reiser, Mark R. (Committee member) / Stufken, John (Committee member) / Welfert, Bruno (Committee member) / Arizona State University (Publisher)
Created2014
Description
Value-added models (VAMs) are used by many states to assess contributions of individual teachers and schools to students' academic growth. The generalized persistence VAM, one of the most flexible in the literature, estimates the ``value added'' by individual teachers to their students' current and future test scores by employing a mixed model with a longitudinal database of test scores. There is concern, however, that missing values that are common in the longitudinal student scores can bias value-added assessments, especially when the models serve as a basis for personnel decisions -- such as promoting or dismissing teachers -- as they are being used in some states. Certain types of missing data require that the VAM be modeled jointly with the missingness process in order to obtain unbiased parameter estimates. This dissertation studies two problems. First, the flexibility and multimembership random effects structure of the generalized persistence model lead to computational challenges that have limited the model's availability. To this point, no methods have been developed for scalable maximum likelihood estimation of the model. An EM algorithm to compute maximum likelihood estimates efficiently is developed, making use of the sparse structure of the random effects and error covariance matrices. The algorithm is implemented in the package GPvam in R statistical software. Illustrations of the gains in computational efficiency achieved by the estimation procedure are given. Furthermore, to address the presence of potentially nonignorable missing data, a flexible correlated random effects model is developed that extends the generalized persistence model to jointly model the test scores and the missingness process, allowing the process to depend on both students and teachers. The joint model gives the ability to test the sensitivity of the VAM to the presence of nonignorable missing data. Estimation of the model is challenging due to the non-hierarchical dependence structure and the resulting intractable high-dimensional integrals. Maximum likelihood estimation of the model is performed using an EM algorithm with fully exponential Laplace approximations for the E step. The methods are illustrated with data from university calculus classes and with data from standardized test scores from an urban school district.
ContributorsKarl, Andrew (Author) / Lohr, Sharon L (Thesis advisor) / Yang, Yan (Thesis advisor) / Kao, Ming-Hung (Committee member) / Montgomery, Douglas C. (Committee member) / Wilson, Jeffrey R (Committee member) / Arizona State University (Publisher)
Created2012
Description
Though the likelihood is a useful tool for obtaining estimates of regression parameters, it is not readily available in the fit of hierarchical binary data models. The correlated observations negate the opportunity to have a joint likelihood when fitting hierarchical logistic regression models. Through conditional likelihood, inferences for the regression and covariance parameters as well as the intraclass correlation coefficients are usually obtained. In those cases, I have resorted to use of Laplace approximation and large sample theory approach for point and interval estimates such as Wald-type confidence intervals and profile likelihood confidence intervals. These methods rely on distributional assumptions and large sample theory. However, when dealing with small hierarchical datasets they often result in severe bias or non-convergence. I present a generalized quasi-likelihood approach and a generalized method of moments approach; both do not rely on any distributional assumptions but only moments of response. As an alternative to the typical large sample theory approach, I present bootstrapping hierarchical logistic regression models which provides more accurate interval estimates for small binary hierarchical data. These models substitute computations as an alternative to the traditional Wald-type and profile likelihood confidence intervals. I use a latent variable approach with a new split bootstrap method for estimating intraclass correlation coefficients when analyzing binary data obtained from a three-level hierarchical structure. It is especially useful with small sample size and easily expanded to multilevel. Comparisons are made to existing approaches through both theoretical justification and simulation studies. Further, I demonstrate my findings through an analysis of three numerical examples, one based on cancer in remission data, one related to the China’s antibiotic abuse study, and a third related to teacher effectiveness in schools from a state of southwest US.
ContributorsWang, Bei (Author) / Wilson, Jeffrey R (Thesis advisor) / Kamarianakis, Ioannis (Committee member) / Reiser, Mark R. (Committee member) / St Louis, Robert (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2017
Description
Correlation is common in many types of data, including those collected through longitudinal studies or in a hierarchical structure. In the case of clustering, or repeated measurements, there is inherent correlation between observations within the same group, or between observations obtained on the same subject. Longitudinal studies also introduce association between the covariates and the outcomes across time. When multiple outcomes are of interest, association may exist between the various models. These correlations can lead to issues in model fitting and inference if not properly accounted for. This dissertation presents three papers discussing appropriate methods to properly consider different types of association. The first paper introduces an ANOVA based measure of intraclass correlation for three level hierarchical data with binary outcomes, and corresponding properties. This measure is useful for evaluating when the correlation due to clustering warrants a more complex model. This measure is used to investigate AIDS knowledge in a clustered study conducted in Bangladesh. The second paper develops the Partitioned generalized method of moments (Partitioned GMM) model for longitudinal studies. This model utilizes valid moment conditions to separately estimate the varying effects of each time-dependent covariate on the outcome over time using multiple coefficients. The model is fit to data from the National Longitudinal Study of Adolescent to Adult Health (Add Health) to investigate risk factors of childhood obesity. In the third paper, the Partitioned GMM model is extended to jointly estimate regression models for multiple outcomes of interest. Thus, this approach takes into account both the correlation between the multivariate outcomes, as well as the correlation due to time-dependency in longitudinal studies. The model utilizes an expanded weight matrix and objective function composed of valid moment conditions to simultaneously estimate optimal regression coefficients. This approach is applied to Add Health data to simultaneously study drivers of outcomes including smoking, social alcohol usage, and obesity in children.
ContributorsIrimata, Kyle (Author) / Wilson, Jeffrey R (Thesis advisor) / Broatch, Jennifer (Committee member) / Kamarianakis, Ioannis (Committee member) / Kao, Ming-Hung (Committee member) / Reiser, Mark R. (Committee member) / Arizona State University (Publisher)
Created2018
Description
Generalized Linear Models (GLMs) are widely used for modeling responses with non-normal error distributions. When the values of the covariates in such models are controllable, finding an optimal (or at least efficient) design could greatly facilitate the work of collecting and analyzing data. In fact, many theoretical results are obtained on a case-by-case basis, while in other situations, researchers also rely heavily on computational tools for design selection.
Three topics are investigated in this dissertation with each one focusing on one type of GLMs. Topic I considers GLMs with factorial effects and one continuous covariate. Factors can have interactions among each other and there is no restriction on the possible values of the continuous covariate. The locally D-optimal design structures for such models are identified and results for obtaining smaller optimal designs using orthogonal arrays (OAs) are presented. Topic II considers GLMs with multiple covariates under the assumptions that all but one covariate are bounded within specified intervals and interaction effects among those bounded covariates may also exist. An explicit formula for D-optimal designs is derived and OA-based smaller D-optimal designs for models with one or two two-factor interactions are also constructed. Topic III considers multiple-covariate logistic models. All covariates are nonnegative and there is no interaction among them. Two types of D-optimal design structures are identified and their global D-optimality is proved using the celebrated equivalence theorem.
Three topics are investigated in this dissertation with each one focusing on one type of GLMs. Topic I considers GLMs with factorial effects and one continuous covariate. Factors can have interactions among each other and there is no restriction on the possible values of the continuous covariate. The locally D-optimal design structures for such models are identified and results for obtaining smaller optimal designs using orthogonal arrays (OAs) are presented. Topic II considers GLMs with multiple covariates under the assumptions that all but one covariate are bounded within specified intervals and interaction effects among those bounded covariates may also exist. An explicit formula for D-optimal designs is derived and OA-based smaller D-optimal designs for models with one or two two-factor interactions are also constructed. Topic III considers multiple-covariate logistic models. All covariates are nonnegative and there is no interaction among them. Two types of D-optimal design structures are identified and their global D-optimality is proved using the celebrated equivalence theorem.
ContributorsWang, Zhongsheng (Author) / Stufken, John (Thesis advisor) / Kamarianakis, Ioannis (Committee member) / Kao, Ming-Hung (Committee member) / Reiser, Mark R. (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2018
Description
In the presence of correlation, generalized linear models cannot be employed to obtain regression parameter estimates. To appropriately address the extravariation due to correlation, methods to estimate and model the additional variation are investigated. A general form of the mean-variance relationship is proposed which incorporates the canonical parameter. The two variance parameters are estimated using generalized method of moments, negating the need for a distributional assumption. The mean-variance relation estimates are applied to clustered data and implemented in an adjusted generalized quasi-likelihood approach through an adjustment to the covariance matrix. In the presence of significant correlation in hierarchical structured data, the adjusted generalized quasi-likelihood model shows improved performance for random effect estimates. In addition, submodels to address deviation in skewness and kurtosis are provided to jointly model the mean, variance, skewness, and kurtosis. The additional models identify covariates influencing the third and fourth moments. A cutoff to trim the data is provided which improves parameter estimation and model fit. For each topic, findings are demonstrated through comprehensive simulation studies and numerical examples. Examples evaluated include data on children’s morbidity in the Philippines, adolescent health from the National Longitudinal Study of Adolescent to Adult Health, as well as proteomic assays for breast cancer screening.
ContributorsIrimata, Katherine E (Author) / Wilson, Jeffrey R (Thesis advisor) / Kamarianakis, Ioannis (Committee member) / Kao, Ming-Hung (Committee member) / Reiser, Mark R. (Committee member) / Stufken, John (Committee member) / Arizona State University (Publisher)
Created2018
Description
With the advent of sophisticated computer technology, we increasingly see the use of computational techniques in the study of problems from a variety of disciplines, including the humanities. In a field such as poetry, where classic works are subject to frequent re-analysis over the course of years, decades, or even centuries, there is a certain demand for fresh approaches to familiar tasks, and such breaks from convention may even be necessary for the advancement of the field. Existing quantitative studies of poetry have employed computational techniques in their analyses, however, there remains work to be done with regards to the deployment of deep neural networks on large corpora of poetry to classify portions of the works contained therein based on certain features. While applications of neural networks to social media sites, consumer reviews, and other web-originated data are common within computational linguistics and natural language processing, comparatively little work has been done on the computational analysis of poetry using the same techniques. In this work, I begin to lay out the first steps for the study of poetry using neural networks. Using a convolutional neural network to classify author birth date, I was able to not only extract a non-trivial signal from the data, but also identify the presence of clustering within by-author model accuracy. While definitive conclusions about the cause of this clustering were not reached, investigation of this clustering reveals immense heterogeneity in the traits of accurately classified authors. Further study may unpack this clustering and reveal key insights about how temporal information is encoded in poetry. The study of poetry using neural networks remains very open but exhibits potential to be an interesting and deep area of work.
ContributorsGoodloe, Oscar Laurence (Author) / Nishimura, Joel (Thesis director) / Broatch, Jennifer (Committee member) / School of Mathematical and Natural Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
As threats to Earth's biodiversity continue to evolve, an effective methodology to predict such threats is crucial to ensure the survival of living species. Organizations like the International Union for Conservation of Nature (IUCN) monitor the Earth's environmental networks to preserve the sanctity of terrestrial and marine life. The IUCN Red List of Threatened Species informs the conservation activities of governments as a world standard of species' risks of extinction. However, the IUCN's current methodology is, in some ways, inefficient given the immense volume of Earth's species and the laboriousness of its species' risk classification process. IUCN assessors can take years to classify a species' extinction risk, even as that species continues to decline. Therefore, to supplement the IUCN's classification process and thus bolster conservationist efforts for threatened species, a Random Forest model was constructed, trained on a group of fish species previously classified by the IUCN Red List. This Random Forest model both validates the IUCN Red List's classification method and offers a highly efficient, supplemental classification method for species' extinction risk. In addition, this Random Forest model is applicable to species with deficient data, which the IUCN Red List is otherwise unable to classify, thus engendering conservationist efforts for previously obscure species. Although this Random Forest model is built specifically for the trained fish species (Sparidae), the methodology can and should be extended to additional species.
ContributorsWoodyard, Megan (Author) / Broatch, Jennifer (Thesis director) / Polidoro, Beth (Committee member) / Mancenido, Michelle (Committee member) / School of Humanities, Arts, and Cultural Studies (Contributor) / School of Mathematical and Natural Sciences (Contributor) / College of Integrative Sciences and Arts (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05