Matching Items (574)
Filtering by
- Creators: Dean, W.P. Carey School of Business
- Resource Type: Text
Description
Many longitudinal studies, especially in clinical trials, suffer from missing data issues. Most estimation procedures assume that the missing values are ignorable or missing at random (MAR). However, this assumption leads to unrealistic simplification and is implausible for many cases. For example, an investigator is examining the effect of treatment on depression. Subjects are scheduled with doctors on a regular basis and asked questions about recent emotional situations. Patients who are experiencing severe depression are more likely to miss an appointment and leave the data missing for that particular visit. Data that are not missing at random may produce bias in results if the missing mechanism is not taken into account. In other words, the missing mechanism is related to the unobserved responses. Data are said to be non-ignorable missing if the probabilities of missingness depend on quantities that might not be included in the model. Classical pattern-mixture models for non-ignorable missing values are widely used for longitudinal data analysis because they do not require explicit specification of the missing mechanism, with the data stratified according to a variety of missing patterns and a model specified for each stratum. However, this usually results in under-identifiability, because of the need to estimate many stratum-specific parameters even though the eventual interest is usually on the marginal parameters. Pattern mixture models have the drawback that a large sample is usually required. In this thesis, two studies are presented. The first study is motivated by an open problem from pattern mixture models. Simulation studies from this part show that information in the missing data indicators can be well summarized by a simple continuous latent structure, indicating that a large number of missing data patterns may be accounted by a simple latent factor. Simulation findings that are obtained in the first study lead to a novel model, a continuous latent factor model (CLFM). The second study develops CLFM which is utilized for modeling the joint distribution of missing values and longitudinal outcomes. The proposed CLFM model is feasible even for small sample size applications. The detailed estimation theory, including estimating techniques from both frequentist and Bayesian perspectives is presented. Model performance and evaluation are studied through designed simulations and three applications. Simulation and application settings change from correctly-specified missing data mechanism to mis-specified mechanism and include different sample sizes from longitudinal studies. Among three applications, an AIDS study includes non-ignorable missing values; the Peabody Picture Vocabulary Test data have no indication on missing data mechanism and it will be applied to a sensitivity analysis; the Growth of Language and Early Literacy Skills in Preschoolers with Developmental Speech and Language Impairment study, however, has full complete data and will be used to conduct a robust analysis. The CLFM model is shown to provide more precise estimators, specifically on intercept and slope related parameters, compared with Roy's latent class model and the classic linear mixed model. This advantage will be more obvious when a small sample size is the case, where Roy's model experiences challenges on estimation convergence. The proposed CLFM model is also robust when missing data are ignorable as demonstrated through a study on Growth of Language and Early Literacy Skills in Preschoolers.
ContributorsZhang, Jun (Author) / Reiser, Mark R. (Thesis advisor) / Barber, Jarrett (Thesis advisor) / Kao, Ming-Hung (Committee member) / Wilson, Jeffrey (Committee member) / St Louis, Robert D. (Committee member) / Arizona State University (Publisher)
Created2013
Description
It is common in the analysis of data to provide a goodness-of-fit test to assess the performance of a model. In the analysis of contingency tables, goodness-of-fit statistics are frequently employed when modeling social science, educational or psychological data where the interest is often directed at investigating the association among multi-categorical variables. Pearson's chi-squared statistic is well-known in goodness-of-fit testing, but it is sometimes considered to produce an omnibus test as it gives little guidance to the source of poor fit once the null hypothesis is rejected. However, its components can provide powerful directional tests. In this dissertation, orthogonal components are used to develop goodness-of-fit tests for models fit to the counts obtained from the cross-classification of multi-category dependent variables. Ordinal categories are assumed. Orthogonal components defined on marginals are obtained when analyzing multi-dimensional contingency tables through the use of the QR decomposition. A subset of these orthogonal components can be used to construct limited-information tests that allow one to identify the source of lack-of-fit and provide an increase in power compared to Pearson's test. These tests can address the adverse effects presented when data are sparse. The tests rely on the set of first- and second-order marginals jointly, the set of second-order marginals only, and the random forest method, a popular algorithm for modeling large complex data sets. The performance of these tests is compared to the likelihood ratio test as well as to tests based on orthogonal polynomial components. The derived goodness-of-fit tests are evaluated with studies for detecting two- and three-way associations that are not accounted for by a categorical variable factor model with a single latent variable. In addition the tests are used to investigate the case when the model misspecification involves parameter constraints for large and sparse contingency tables. The methodology proposed here is applied to data from the 38th round of the State Survey conducted by the Institute for Public Policy and Michigan State University Social Research (2005) . The results illustrate the use of the proposed techniques in the context of a sparse data set.
ContributorsMilovanovic, Jelena (Author) / Young, Dennis (Thesis advisor) / Reiser, Mark R. (Thesis advisor) / Wilson, Jeffrey (Committee member) / Eubank, Randall (Committee member) / Yang, Yan (Committee member) / Arizona State University (Publisher)
Created2011
Description
Designing a hazard intelligence platform enables public agencies to organize diversity and manage complexity in collaborative partnerships. To maintain the integrity of the platform while preserving the prosocial ethos, understanding the dynamics of “non-regulatory supplements” to central governance is crucial. In conceptualization, social responsiveness is shaped by communicative actions, in which coordination is attained through negotiated agreements by way of the evaluation of validity claims. The dynamic processes involve information processing and knowledge sharing. The access and the use of collaborative intelligence can be examined by notions of traceability and intelligence cohort. Empirical evidence indicates that social traceability is statistical significant and positively associated with the improvement of collaborative performance. Moreover, social traceability positively contributes to the efficacy of technical traceability, but not vice versa. Furthermore, technical traceability significantly contributes to both moderate and high performance improvement; while social traceability is only significant for moderate performance improvement. Therefore, the social effect is limited and contingent. The results further suggest strategic considerations. Social significance: social traceability is the fundamental consideration to high cohort performance. Cocktail therapy: high cohort performance involves an integrative strategy with high social traceability and high technical traceability. Servant leadership: public agencies should exercise limited authority and perform a supporting role in the provision of appropriate technical traceability, while actively promoting social traceability in the system.
ContributorsWang, Chao-shih (Author) / Van Fleet, David (Thesis advisor) / Grebitus, Carola (Committee member) / Wilson, Jeffrey (Committee member) / Shultz, Clifford (Committee member) / Arizona State University (Publisher)
Created2015
Description
The Pearson and likelihood ratio statistics are well-known in goodness-of-fit testing and are commonly used for models applied to multinomial count data. When data are from a table formed by the cross-classification of a large number of variables, these goodness-of-fit statistics may have lower power and inaccurate Type I error rate due to sparseness. Pearson's statistic can be decomposed into orthogonal components associated with the marginal distributions of observed variables, and an omnibus fit statistic can be obtained as a sum of these components. When the statistic is a sum of components for lower-order marginals, it has good performance for Type I error rate and statistical power even when applied to a sparse table. In this dissertation, goodness-of-fit statistics using orthogonal components based on second- third- and fourth-order marginals were examined. If lack-of-fit is present in higher-order marginals, then a test that incorporates the higher-order marginals may have a higher power than a test that incorporates only first- and/or second-order marginals. To this end, two new statistics based on the orthogonal components of Pearson's chi-square that incorporate third- and fourth-order marginals were developed, and the Type I error, empirical power, and asymptotic power under different sparseness conditions were investigated. Individual orthogonal components as test statistics to identify lack-of-fit were also studied. The performance of individual orthogonal components to other popular lack-of-fit statistics were also compared. When the number of manifest variables becomes larger than 20, most of the statistics based on marginal distributions have limitations in terms of computer resources and CPU time. Under this problem, when the number manifest variables is larger than or equal to 20, the performance of a bootstrap based method to obtain p-values for Pearson-Fisher statistic, fit to confirmatory dichotomous variable factor analysis model, and the performance of Tollenaar and Mooijaart (2003) statistic were investigated.
ContributorsDassanayake, Mudiyanselage Maduranga Kasun (Author) / Reiser, Mark R. (Thesis advisor) / Kao, Ming-Hung (Committee member) / Wilson, Jeffrey (Committee member) / St. Louis, Robert (Committee member) / Kamarianakis, Ioannis (Committee member) / Arizona State University (Publisher)
Created2018
Description
This project uses Kenneth Burke’s theory of dramatism and the pentad to analyze popular narrative films about human sex trafficking. It seeks to understand the relationship between a film’s dominant philosophy (as highlighted by utilizing Burke’s pentad), its inherently suggested solutions to trafficking, and the effect that the film has on viewers’ perception of trafficking. 20 narrative feature films about sex trafficking such as the 2008 film Taken were analyzed for this study. Three out of five of Burke’s philosophies were uncovered after analysis: idealism, mysticism, and materialism. Films that aligned with idealism were found to implicitly blame women for their own trafficking. Films that aligned with mysticism were found to rally audiences around violence and racism as opposed to women’s freedom. Films that aligned with materialism were found to be the most empathetic towards trafficked women. The conclusion of this paper is that films about sex trafficking have a high potential to be harmful to women who have exited trafficking. This paper asserts that the most valuable films about trafficking are those that are not simply based on a true story but are created by trafficking survivors themselves, such as the 2016 film Apartment 407.
ContributorsHamby, Hannah Mary (Co-author) / Raum, Brionna (Co-author) / Edson, Belle (Thesis director) / Zanin, Alaina (Committee member) / Dean, W.P. Carey School of Business (Contributor) / Hugh Downs School of Human Communication (Contributor) / School of Film, Dance and Theatre (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
This document is a proposal for a research project, submitted as an Honors Thesis to Barrett, The Honors College at Arizona State University. The proposal summarizes previous findings and literature about women survivors of domestic violence who are suffering from post-traumatic stress disorder as well as outlining the design and measures of the study. At this time, the study has not been completed. However, it may be completed at a future time.
ContributorsKunst, Jessica (Author) / Hernandez Ruiz, Eugenia (Thesis director) / Belgrave, Melita (Committee member) / School of Music (Contributor) / Dean, W.P. Carey School of Business (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Service providers in the hotel industry are interested in identifying the factors that contribute to consumers' choice of hotel booking method. In an effort to determine these factors we used the predictive analytic tool of logistic regression. In particular, we concentrated on the choice of booking directly on a hotel website as compared to a third-party website. We found that consumers with children were 2.94 times more likely to use a hotel's website. We found that consumers who place a high importance on cost were 1.42 times more likely to use a third-party website for booking a hotel. These results could be useful for hotel marketing and sales representatives to better understand the preferences of their customers and improve the hotel reservation services provided. Predicting consumer needs and choices have the potential to optimize sales and increase profits.
ContributorsMolinaro, Erin Rose (Author) / Wilson, Jeffrey (Thesis director) / Dawson, Gregory (Committee member) / Barrett, The Honors College (Contributor) / Department of Supply Chain Management (Contributor) / Department of Finance (Contributor) / W. P. Carey School of Business (Contributor)
Created2015-05
Description
While there are many characteristics that make up a woman, femininity is one that is difficult to define because it is a communication and expression practice defined by culture. This research explores historical accounts of femininity in the 1950s as seen through the exemplar of the white, middle-class "happy homemaker" or "happy housewife." The 1950s is important to study in light of changing gender and social dynamics due to the transition from World War II to a period of prosperity. By using primary sources from the 1950s and secondary historical analyses, this research takes the form of a sociological accounting of 1950s' femininity and the lessons that can be applied today. Four cultural forces led to homemakers having an unspoken identity crisis because they defined themselves in terms of relationship with others and struggled to uphold a certain level of femininity. The forces are: the feminine mystique, patriotism, cultural normalcy, and unnecessary choices. These forces caused women to have unhealthy home relationships in their marriages and motherhood while persistently doing acts to prove their self-worth, such as housework and consuming. It is important to not look back at the 1950s as an idyllic time without also considering the social and cultural practices that fostered a feminine conformity in women. Today, changes can be made to allow women to express femininity in modern ways by adapting to reality instead of to outdated values. For example, changes in maternity leave policies allow women to be mothers and still be in the workforce. Additionally, women should find fulfillment in themselves by establishing a strong personal identity and confidence in their womanhood before identifying through other people or through society.
ContributorsHeinauer, Richelle Diane (Author) / Brouwer, Daniel (Thesis director) / Haskin, Jennifer (Committee member) / Hugh Downs School of Human Communication (Contributor) / Sanford School of Social and Family Dynamics (Contributor) / Dean, W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
The Centers for Disease Control and Prevention in the United States announced that there has been roughly a 50% increase in the prevalence of food allergies among people between the years of 1997 - 2011. A food allergy can be described as a medical condition where being exposed to a certain food triggers a harmful immune response in the body, known as an allergic reaction. These reactions can range from mild to fatal, and they are caused mainly by the top 8 major food allergens: dairy, eggs, peanuts, tree nuts, wheat, soy, fish, and shellfish. Food allergies mainly plague children under the age of 3, as some of them will grow out of their allergy sensitivity over time, and most people develop their allergies at a young age, and not when they are older. The rise in prevalence is becoming a frightening problem around the world, and there are emerging theories that are attempting to ascribe a cause. There are three well-known hypotheses that will be discussed: the Hygiene Hypothesis, the Dual-Allergen Exposure Hypothesis, and the Vitamin-D Deficiency Hypothesis. Beyond that, this report proposes that a new hypothesis be studied, the Food Systems Hypothesis. This hypothesis theorizes that the cause of the rise of food allergies is actually caused by changes in the food itself and particularly the pesticides that are used to cultivate it.
ContributorsCromer, Kelly (Author) / Lee, Rebecca (Thesis director) / MacFadyen, Joshua (Committee member) / Sanford School of Social and Family Dynamics (Contributor) / Dean, W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
Fashion is individual in its expression. It is also universal. Fashion is a cumulation of different influences and different interpretations. We currently live in a climate divided by race, culture, gender, and so much more. It is so difficult to find common ground on a global platform. Something that stands alone is fashion. Fashion is influenced by so many aspects. Of these, aspects that I am interested in are culture and sustainability. When combined with culture, fashion can anchor and have a root to the generations that came before us. When combined with sustainability, we have an anchor to the planet that we share with everyone. The result of fashion is always the same, beautiful art. I want people to see the beauty not only in the art itself, but the differences and similarities that such art provides. We all come from the same world but have different ways of expressing that world. My goal is to show people that they need to acknowledge the differences but can choose to see the similarities of each culture. Additionally, I redesign garments that capture an emotion and a story. Making each piece individual yet serving a greater purpose sustainability wise. I envision the principle of sustainable fashion to be the basis of each piece of clothing. Therefore, for my creative project I am constructing five art pieces representing five cultures that has had a significant influence on my life and personal style. These cultures are those of UAE, Germany, Nepal, Mexico, and Spain. Each of these garments are made from recycled fabric and clothing donated by family and friends. My objective is to display sustainable fashion that has deep cultural influence. Every piece has a story and an emotion attached as well to create a connection with the clothing itself.
ContributorsKreiser, Samantha Miren (Author) / Chhetri, Nalini (Thesis director) / Ellis, Naomi (Committee member) / Dean, W.P. Carey School of Business (Contributor, Contributor) / Department of Economics (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05