Matching Items (18)
Filtering by
- Genre: Doctoral Dissertation
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
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
The goal of diagnostic assessment is to discriminate between groups. In many cases, a binary decision is made conditional on a cut score from a continuous scale. Psychometric methods can improve assessment by modeling a latent variable using item response theory (IRT), and IRT scores can subsequently be used to determine a cut score using receiver operating characteristic (ROC) curves. Psychometric methods provide reliable and interpretable scores, but the prediction of the diagnosis is not the primary product of the measurement process. In contrast, machine learning methods, such as regularization or binary recursive partitioning, can build a model from the assessment items to predict the probability of diagnosis. Machine learning predicts the diagnosis directly, but does not provide an inferential framework to explain why item responses are related to the diagnosis. It remains unclear whether psychometric and machine learning methods have comparable accuracy or if one method is preferable in some situations. In this study, Monte Carlo simulation methods were used to compare psychometric and machine learning methods on diagnostic classification accuracy. Results suggest that classification accuracy of psychometric models depends on the diagnostic-test correlation and prevalence of diagnosis. Also, machine learning methods that reduce prediction error have inflated specificity and very low sensitivity compared to the data-generating model, especially when prevalence is low. Finally, machine learning methods that use ROC curves to determine probability thresholds have comparable classification accuracy to the psychometric models as sample size, number of items, and number of item categories increase. Therefore, results suggest that machine learning models could provide a viable alternative for classification in diagnostic assessments. Strengths and limitations for each of the methods are discussed, and future directions are considered.
ContributorsGonzález, Oscar (Author) / Mackinnon, David P (Thesis advisor) / Edwards, Michael C (Thesis advisor) / Grimm, Kevin J. (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2018
Description
Guided by Tinto’s Theory of College Student Departure, I conducted a set of five studies to identify factors that influence students’ social integration in college science active learning classes. These studies were conducted in large-enrollment college science courses and some were specifically conducted in undergraduate active learning biology courses. Using qualitative and quantitative methodologies, I identified how students’ identities, such as their gender and LGBTQIA identity, and students’ perceptions of their own intelligence influence their experience in active learning science classes and consequently their social integration in college. I also determined factors of active learning classrooms and instructor behaviors that can affect whether students experience positive or negative social integration in the context of active learning. I found that students’ hidden identities, such as the LGBTQIA identity, are more relevant in active learning classes where students work together and that the increased relevance of one’s identity can have a positive and negative impact on their social integration. I also found that students’ identities can predict their academic self-concept, or their perception of their intelligence as it compares to others’ intelligence in biology, which in turn predicts their participation in small group-discussion. While many students express a fear of negative evaluation, or dread being evaluated negatively by others when speaking out in active learning classes, I identified that how instructors structure group work can cause students to feel more or less integrated into the college science classroom. Lastly, I identified tools that instructors can use, such as name tents and humor, which can positive affect students’ social integration into the college science classroom. In sum, I highlight inequities in students’ experiences in active learning science classrooms and the mechanisms that underlie some of these inequities. I hope this work can be used to create more inclusive undergraduate active learning science courses.
ContributorsCooper, Katelyn M (Author) / Brownell, Sara E (Thesis advisor) / Stout, Valerie (Committee member) / Collins, James (Committee member) / Orchinik, Miles (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2018
Description
The Pearson and likelihood ratio statistics are commonly used to test goodness-of-fit for models applied to data from a multinomial distribution. When data are from a table formed by cross-classification of a large number of variables, the common statistics may have low power and inaccurate Type I error level due to sparseness in the cells of the table. The GFfit statistic can be used to examine model fit in subtables. It is proposed to assess model fit by using a new version of GFfit statistic based on orthogonal components of Pearson chi-square as a diagnostic to examine the fit on two-way subtables. However, due to variables with a large number of categories and small sample size, even the GFfit statistic may have low power and inaccurate Type I error level due to sparseness in the two-way subtable. In this dissertation, the theoretical power and empirical power of the GFfit statistic are studied. A method based on subsets of orthogonal components for the GFfit statistic on the subtables is developed to improve the performance of the GFfit statistic. Simulation results for power and type I error rate for several different cases along with comparisons to other diagnostics are presented.
ContributorsZhu, Junfei (Author) / Reiser, Mark R. (Thesis advisor) / Stufken, John (Committee member) / Zheng, Yi (Committee member) / St Louis, Robert (Committee member) / Kao, Ming-Hung (Committee member) / Arizona State University (Publisher)
Created2017
Description
In this mixed-methods study, I sought to design and develop a test delivery method to reduce linguistic bias in English-based mathematics tests. Guided by translanguaging, a recent linguistic theory recognizing the complexity of multilingualism, I designed a computer-based test delivery method allowing test-takers to toggle between English and their self-identified dominant language. This three-part study asks and answers research questions from all phases of the novel test delivery design. In the first phase, I conducted cognitive interviews with 11 Mandarin Chinese dominant speakers and 11 Spanish speaking dominant undergraduate students while taking a well-regarded calculus conceptual exam, the Precalculus Concept Assessment (PCA). In the second phase, I designed and developed the linguistically adaptive test (LAT) version of the PCA using the Concerto test delivery platform. In the third phase, I conducted a within-subjects random-assignment study of the efficacy the LAT. I also conducted in-depth interviews with a subset of the test-takers.
Nine items on the PCA revealed linguistic issues during the cognitive interviews demonstrating the need to improve the linguistic bias on the test items. Additionally, the newly developed LAT demonstrated evidence of reliability and validity. However, the large-scale efficacy study showed that the LAT did not appear to make a significant difference in scores for dominant speakers of Spanish or dominant speakers of Mandarin Chinese. This finding held true for overall test scores as well as at the item level indicating that the LAT test delivery system does not appear to reduce linguistic bias in testing.
Additionally, in-depth interviews revealed that many students felt that the linguistically adaptive test was either the same or essentially the same as the non-LAT version of the test. Some participants felt that the toggle button was not necessary if they could understand the mathematics item well enough. As one participant noted, “It's math, It's math. It doesn't matter if it's in English or in Spanish.” This dissertation concludes with a discussion about the implications for test developers and suggestions for future direction of study.
ContributorsClose, Kevin (Author) / Zheng, Yi (Thesis advisor) / Amrein-Beardsley, Audrey (Thesis advisor) / Anderson, Kate (Committee member) / Arizona State University (Publisher)
Created2021
Description
This dissertation comprises two projects: (i) Multiple testing of local maxima for detection of peaks and change points with non-stationary noise, and (ii) Height distributions of critical points of smooth isotropic Gaussian fields: computations, simulations and asymptotics. The first project introduces a topological multiple testing method for one-dimensional domains to detect signals in the presence of non-stationary Gaussian noise. The approach involves conducting tests at local maxima based on two observation conditions: (i) the noise is smooth with unit variance and (ii) the noise is not smooth where kernel smoothing is applied to increase the signal-to-noise ratio (SNR). The smoothed signals are then standardized, which ensures that the variance of the new sequence's noise becomes one, making it possible to calculate $p$-values for all local maxima using random field theory. Assuming unimodal true signals with finite support and non-stationary Gaussian noise that can be repeatedly observed. The algorithm introduced in this work, demonstrates asymptotic strong control of the False Discovery Rate (FDR) and power consistency as the number of sequence repetitions and signal strength increase. Simulations indicate that FDR levels can also be controlled under non-asymptotic conditions with finite repetitions. The application of this algorithm to change point detection also guarantees FDR control and power consistency. The second project focuses on investigating the explicit and asymptotic height densities of critical points of smooth isotropic Gaussian random fields on both Euclidean space and spheres.The formulae are based on characterizing the distribution of the Hessian of the Gaussian field using the Gaussian orthogonally invariant (GOI) matrices and the Gaussian orthogonal ensemble (GOE) matrices, which are special cases of GOI matrices. However, as the dimension increases, calculating explicit formulae becomes computationally challenging. The project includes two simulation methods for these distributions. Additionally, asymptotic distributions are obtained by utilizing the asymptotic distribution of the eigenvalues (excluding the maximum eigenvalues) of the GOE matrix for large dimensions. However, when it comes to the maximum eigenvalue, the Tracy-Widom distribution is utilized. Simulation results demonstrate the close approximation between the asymptotic distribution and the real distribution when $N$ is sufficiently large.
Contributorsgu, shuang (Author) / Cheng, Dan (Thesis advisor) / Lopes, Hedibert (Committee member) / Fricks, John (Committee member) / Lan, Shiwei (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2023
Description
This dissertation explores applications of machine learning methods in service of the design of screening tests, which are ubiquitous in applications from social work, to criminology, to healthcare. In the first part, a novel Bayesian decision theory framework is presented for designing tree-based adaptive tests. On an application to youth delinquency in Honduras, the method produces a 15-item instrument that is almost as accurate as a full-length 150+ item test. The framework includes specific considerations for the context in which the test will be administered, and provides uncertainty quantification around the trade-offs of shortening lengthy tests. In the second part, classification complexity is explored via theoretical and empirical results from statistical learning theory, information theory, and empirical data complexity measures. A simulation study that explicitly controls two key aspects of classification complexity is performed to relate the theoretical and empirical approaches. Throughout, a unified language and notation that formalizes classification complexity is developed; this same notation is used in subsequent chapters to discuss classification complexity in the context of a speech-based screening test. In the final part, the relative merits of task and feature engineering when designing a speech-based cognitive screening test are explored. Through an extensive classification analysis on a clinical speech dataset from patients with normal cognition and Alzheimer’s disease, the speech elicitation task is shown to have a large impact on test accuracy; carefully performed task and feature engineering are required for best results. A new framework for objectively quantifying speech elicitation tasks is introduced, and two methods are proposed for automatically extracting insights into the aspects of the speech elicitation task that are driving classification performance. The dissertation closes with recommendations for how to evaluate the obtained insights and use them to guide future design of speech-based screening tests.
ContributorsKrantsevich, Chelsea (Author) / Hahn, P. Richard (Thesis advisor) / Berisha, Visar (Committee member) / Lopes, Hedibert (Committee member) / Renaut, Rosemary (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2023
Description
Integrating agent-based models (ABMs) has been a popular approach for teaching emergent science concepts. However, students continue to find it difficult to explain the emergent process of natural selection. This study adopted an ontological framework–the Pattern, Agents, Interactions, Relations, and Causality (PAIR-C)–to guide the design of learning modules. This pre-posttest experimental study examines the effects of the PAIR-C module versus the Regular module on fostering students’ deep understanding of natural selection. Results show that students in the PAIR-C intervention group performed better in answering deep questions assessing the understanding of inter-level causal relationships than those in the Regular control group. Although students in both groups did not show significantly improved abilities in explaining the natural selection process for other contexts or significant differences in their abilities to explain other emergent phenomena, students in the intervention group demonstrated system-thinking perspectives and fewer misconceptions in their expressions compared to the control group. A close analysis of student misconceptions consolidates that the intervention group demonstrated drastically fewer categories and numbers of misconceptions while those in the control group did not show such drastic changes before and after the study. To precisely address misconceptions and further improve students’ learning outcomes, Epistemic Network Analysis was adopted to capture students’ misconception characteristics by examining the co-occurrences of different misconception categories as well as the relationship between misconceptions and PAIR-C features. The results of student learning outcomes and misconception characteristics collectively provide directions for improving the instructional design of the PAIR-C module. Furthermore, findings on student engagement levels during learning can also inform future design efforts. Overall, this project sheds light on applying an innovative framework to designing effective learning modules to teach emergent science concepts.
ContributorsSu, Man (Author) / Chi, Michelene (Thesis advisor) / Nelson, Brian (Committee member) / Zheng, Yi (Committee member) / Arizona State University (Publisher)
Created2023
Description
Goodness-of-fit test is a hypothesis test used to test whether a given model fit the data well. It is extremely difficult to find a universal goodness-of-fit test that can test all types of statistical models. Moreover, traditional Pearson’s chi-square goodness-of-fit test is sometimes considered to be an omnibus test but not a directional test so it is hard to find the source of poor fit when the null hypothesis is rejected and it will lose its validity and effectiveness in some of the special conditions. Sparseness is such an abnormal condition. One effective way to overcome the adverse effects of sparseness is to use limited-information statistics. In this dissertation, two topics about constructing and using limited-information statistics to overcome sparseness for binary data will be included. In the first topic, the theoretical framework of pairwise concordance and the transformation matrix which is used to extract the corresponding marginals and their generalizations are provided. Then a series of new chi-square test statistics and corresponding orthogonal components are proposed, which are used to detect the model misspecification for longitudinal binary data. One of the important conclusions is, the test statistic $X^2_{2c}$ can be taken as an extension of $X^2_{[2]}$, the second-order marginals of traditional Pearson’s chi-square statistic. In the second topic, the research interest is to investigate the effect caused by different intercept patterns when using Lagrange multiplier (LM) test to find the source of misfit for two items in 2-PL IRT model. Several other directional chi-square test statistics are taken into comparison. The simulation results showed that the intercept pattern does affect the performance of goodness-of-fit test, especially the power to find the source of misfit if the source of misfit does exist. More specifically, the power is directly affected by the `intercept distance' between two misfit variables. Another discovery is, the LM test statistic has the best balance between the accurate Type I error rates and high empirical power, which indicates the LM test is a robust test.
ContributorsXu, Jinhui (Author) / Reiser, Mark (Thesis advisor) / Kao, Ming-Hung (Committee member) / Wilson, Jeffrey (Committee member) / Zheng, Yi (Committee member) / Edwards, Michael (Committee member) / Arizona State University (Publisher)
Created2022