Search Results (1 - 25 of 79 Results)

Sort By  
Sort Dir
 
Results per page  

Sanders, MargaretMultifactor Models of Ordinal Data: Comparing Four Factor Analytical Methods
Master of Arts, The Ohio State University, 2014, EDU Policy and Leadership
In education research, ordinal data is the norm but does not meet the assumptions of most statistical methods and thus is often analyzed inappropriately. Using a dataset typical of the field, this study compared four factor analytic methods: a traditional exploratory factor analysis (EFA), a full-information EFA, and two EFAs within the confirmatory factor analysis framework (E/CFA) conducted according to the Jöreskog method and the Gugiu method. Because an approach for handling cross-loaded items in multifactor models has not been clearly defined within the Gugiu method, two approaches were compared. The fixed-loadings approach involves forcing cross-loaded items to load onto only one factor, chosen based on the strongest theoretical justification. The delete-items approach deletes all cross-loaded items from the model. Both approaches were used to arrive at a starting model that was then modified according to the Gugiu method. Methods were compared on initial model fit, replication in a confirmatory factor analysis, and the stability, interpretability, and reliability of the models. In terms of initial model fit, methods appropriate for ordinal data produced better models, the E/CFAs outperformed the EFAs, and the Gugiu method demonstrated greater model interpretability than the Jöreskog method. Both approaches to the Gugiu method produced well-fitting models, but the delete-items approach outperformed the fixed-loadings approach. However, contrary to the findings of a previous study, these results did not hold for model validation. In CFAs conducted on posttest data, the model fit of the E/CFAs was on par with or worse than the model fit of the EFAs. Additionally, the two approaches to the Gugiu method performed the worst where before they had performed the best, with the fixed-loadings approach faring particularly poorly. In the case of this data, the full-information EFA produced the best fitting models. Examining characteristics of the data help to explain the unexpectedly poor performance of the E/CFA methods and help to clarify when these methods are appropriate to use. Diagonal weighted least squares (DWLS), the method of estimation employed by the full-information EFA and the two E/CFAs, may produce biased parameter estimates when used with small sample sizes, with factors defined by only a few items, and with items with high skewness. These biased parameter estimates are even more problematic when used to make model modification decisions, as they were for the Jöreskog and Gugiu E/CFA methods. Thus, the results of the current study suggest that the full-information EFA may be the most appropriate method to use with data with these problematic characteristics. Secondarily, the findings also provide evidence for the delete-items approach as the more appropriate way of dealing with cross-loaded items in the Gugiu E/CFA method.

Committee:

P. Cristian Gugiu (Advisor); Eric Anderman (Committee Member)

Subjects:

Educational Tests and Measurements; Psychological Tests

Keywords:

exploratory factor analysis; confirmatory factor analysis; ordinal data analysis

Wang, JingAnalogy Between Two Approaches to Separately Identify Specific Factors in Factor Analysis
Doctor of Philosophy (Ph.D.), Bowling Green State University, 2007, Psychology/Quantitative
An observed variable may be decomposed into three components: one or several common factors, a specific factor, and a measurement error. Unfortunately, the specific factor is usually combined with the measurement error and treated as the unique factor in a factor analytic model (FAM) (Harman, 1976; Muliak, 1972). The confounding of parameters leads to several potential problems, such as underestimated reliability, biased estimation of the intercepts, slopes, and measurement error variances. There are two approaches to separately identify the specific factors, the first- and second-order FAM approach and the stationary longitudinal FAM approach, both by including several replicates for each variable from a classical FAM. The purpose of the dissertation is to fully discuss the analogy between the two approaches on separately identifying the specific factors and highlight the role played by the specific factors. First, the first- and second-order FAM approach is extended by including the mean structure and explicitly including the specific factor means and variances. Second, a special condition, i.e., equality of specific factor variances and covariances for the same variable, in the stationery longitudinal FAM approach is presented. To show the analogy between the two approaches on the model identification, all observed and latent variables are permutated to be variable ordered for the longitudinal model. After the permutations, we can easily see that the special condition allows us to build a second-order model on the specific factors, which shows the similarity between the two approaches. However, the first approach requires equal specific factor means for the replicates, while the second approach allows the specific factor means to change over time. From one illustration in a longitudinal FAM, the presence of the specific factors, exhibits themselves both in the mean structure, and in the variance/covariances structure. If the specific factors were omitted, the desired stationarity of the factor structure, i.e., equal intercepts and slopes, would be biased. Furthermore, neglecting the specific factors would lead to negatively biased reliabilities.

Committee:

John Tisak (Advisor)

Subjects:

Psychology, Psychometrics

Keywords:

SPECIFIC FACTOR; LONGITUDINAL FACTOR ANALYSIS; FACTORIAL INVARIANCE; SECOND-ORDER FACTOR ANALYSIS

McGuffey, Amy R.Validity and Utility of the Comprehensive Assessment of School Environment (CASE) Survey
Doctor of Philosophy (Ph.D.), University of Dayton, 2014, Educational Leadership
Despite the constant demands placed on schools to excel academically, there is a combination of core components necessary for school systems to be successful. Although schools want to offer a climate that is conducive to all of their stakeholders (staff, students, and family members) many of them strive to understand the existing climate and the impact it has on the school. Because measuring climate is difficult many schools struggle to find a valid means of gathering information in order to improve the school climate. The National Association of Secondary School Principals (NASSP) designed a second version of the Comprehensive Assessment of School Environment (CASE) survey to measure school climate in 2010 (the original version was designed in 1986) and, to date, it had not been validated. According to NASSP, the information gained from the survey can be utilized by schools to make better decisions for school improvement. The purpose of this research was to evaluate the construct validity of the 2010 version of CASE through exploratory factor analysis. Additionally, the researcher also analyzed the usability of the instrument’s design, clarity, and ease of use by intended stakeholders at the local school level. The entry points for data collection in schools were a national random sample of high school principals (N=28) who were members of the National Association of Secondary Principals. The principals distributed an online link to the survey to the staff, students, and parents/guardians in their buildings, consistent with the CASE design. Over 4,000 stakeholders representing 28 schools across 21 states completed the CASE survey. A four-factor solution was derived from a factor analysis of combined responses from three groups of stakeholders (students, parents, and instructional staff). The four factors retained were: (1) Savvy Teaching Practices, (2) Student Responsibility and Safety, (3) Cohesive School Relationships and Belonging, and (4) Positive Environmental Structures. Descriptive statistics were conducted to examine the utility of the CASE survey. The findings, with no mean score less than 5 (on a 6-point scale), suggest that stakeholders found the CASE survey to be a useable instrument.

Committee:

Carolyn Ridenour, Ed.D. (Committee Chair); Thomas Lasley, Ph.D. (Committee Member); Charles Russo, Ed.D. (Committee Member); Keri Kirschman, Ph.D (Committee Member)

Subjects:

Education; Educational Leadership; Educational Tests and Measurements

Keywords:

CASE; Comprehensive Assessment of School Environment; validity; factor analysis; utility; exploratory factor analysis; school climate; psychometric

Climer, Amy EThe Development of the Creative Synergy Scale
Ph.D., Antioch University, 2016, Leadership and Change
This study developed a scale for teams to assess their behaviors related to creative synergy. Creative synergy is the interactions among team members where the collective creative results are greater than the sum of their individual efforts. When a team achieves creative synergy they have the potential to solve difficult problems with innovative solutions leading to positive impacts on our communities, societies, and even our world. This study looked at the internal-process variables of teams to determine what factors impact creative synergy. The research process involved two phases. In Phase 1, a survey was taken by 830 adults who were members of teams. The results were analyzed using exploratory and confirmatory factor analysis. A new scale was created that identified three factors teams need for creative synergy: team purpose, team dynamics, and team creative process. In Phase 2, the new scale was tested with three work teams to determine the perceived accuracy of the scale. The new Creative Synergy Scale will be a valuable tool for teams wanting to be more creative together. It will give them feedback on their level of team purpose, team dynamics, and team creative process. This dissertation is accompanied by two supplemental files: a video of the author’s introduction (MP4) and a correlation table showing the original 75 items considered for the Creative Synergy Scale (PDF). This dissertation is available in open-access at OhioLink ETD Center, etd.ohiolink.edu and AURA: Antioch University Repository and Archive, http://aura.antioch.edu/

Committee:

Mitchell Kusy, Ph.D (Committee Chair); Carol Baron, Ph.D (Committee Member); Susan Keller-Mathers, Ed.D (Committee Member); James Kaufman, Ph.D (Other)

Subjects:

Behavioral Psychology; Behavioral Sciences; Behaviorial Sciences; Business Administration; Business Community; Cognitive Psychology; Communication; Management; Organization Theory; Organizational Behavior; Psychological Tests; Psychology; Social Psychology; Social Research; Statistics

Keywords:

creative synergy; creative behavior; creativity; innovation; teams; business teams; adult work teams; adults; creative teams; innovative teams; creative problem solving; scale; exploratory factor analysis; confirmatory factor analysis

Farouni, TarekLatent Variable Models of Categorical Responses in the Bayesian and Frequentist Frameworks
Master of Arts, The Ohio State University, 2014, Psychology
The thesis consists of two self-contained manuscripts. The first manuscript presents a Bayesian multilevel formulation of a cross-classified latent variable model for categorical responses. In the manuscript, we discuss the issue of model non-identifiability and how parameter constraints in the form of item-level regression covariates can aid in model identification. We use the latent regression identification strategy to fit one of two models that we propose to examine the latent structure of emotional distress regarding aspects of anxiety and depression. The models are fit to an empirical dataset consisting of item responses on the Patient-Reported Outcomes Measurement Information System (PROMIS) profile of emotional distress. The second manuscript expands upon methodological issues outlined in Halpin et al. (2014) that involve the problem of identifiability of a two-dimensional CFA model. In the manuscript, we incorporate the nonlinearity brought about by the discreteness of the response variable in the model's specification. The identification of the resulting Categorical Item Factor Analysis (CIFA) model with mixed dichotomous and ordinal responses is examined and some of the results already published in Halpin et al. (2014) regarding identification are re-derived and expanded upon accordingly. We also propose and examine a theoretically informed parameter constraint in which the crossloading parameters are a deterministic function of the anxiety latent variable. The proposed constraint adds a quadratic latent variable in the model rendering the latent space nonlinear. The two types of nonlinearity result in a mixed-response nonlinear categorical item factor analysis model which can be formulated as the conditional distribution of a generalized linear mixed model with the logit link function. The model is then fit to an empirical dataset and a Monte Carlo simulation study is performed.

Committee:

Paul De Boeck (Advisor); Bob Cudeck (Committee Member); Michael Edwards (Committee Member)

Subjects:

Educational Tests and Measurements; Psychology; Statistics

Keywords:

Psychometrics; Latent Variable Model; Model Identifiability; Categorical Item Factor Analysis; Bayesian Cross-classified Multilevel Model; Multidimensional IRT; Nonlinear Factor Analysis

King, Holly MTeacher Affective Attitudes Inventory: Development and Validation of a Teacher Self-Assessment Instrument
Ph.D., Antioch University, 2017, Leadership and Change
This study developed a teacher self-assessment instrument in the form of six factors across two overarching constructs, resulting in one Positive Relationships scale with three factors; and three related, but separate, scales measuring elements of the Classroom Environment. Many teacher skills and qualities are known to contribute to effectiveness in the classroom, such as teacher self-efficacy, content knowledge, pedagogical knowledge, and instructional knowledge. The inclusion of affective dimensions of teacher effectiveness can complement the prevailing focus on other measures of teacher effectiveness, through the consideration of critically important, but relatively ignored, aspects of effective teaching. This study examined teacher attitudes toward building positive relationships with students and creating an empowering classroom environment, grounded in teacher effectiveness research. A survey was taken by 403 practicing elementary teachers in the United States. The results were analyzed using exploratory and confirmatory factor analysis. The resulting factors were compared with a four-item classroom management subscale of the Teachers’ Sense of Efficacy Scale (Tschannen-Moran & Woolfolk Hoy, 2001) to determine convergent validity, measuring similar underlying constructs; and divergent validity, measuring attitudes versus efficacy. Participant demographic variables were compared using independent sample t-tests, one-way ANOVA, and tests for metric invariance to determine if the instrument performed similarly with all groups. Findings show good model fit, reliability, and validity for the factors related to each overarching construct, and most demographic variables showed no variance in the models. Significant differences were found for the Managing Conflict factor between teachers who taught grades K–2 and teachers who taught all elementary grades. Group differences on the Student-Centered and Positive Guidance factors were found between teachers identifying as White and teachers identifying as other than White. The research study concludes by offering implications for teacher formative assessment, iv guidance for professional learning, implications for educational leadership, and questions for future research. This dissertation is accompanied by three supplemental files: a video of the author’s introduction (MP4) and two correlation tables showing the original 61 items considered for the two proposed scales. This dissertation is available in open access at AURA: Antioch University Repository and Archive, http://aura.antioch.edu/, and OhioLINK ETD Center, https://edt.ohiolink.edu

Committee:

Jon Wergin, Ph.D. (Committee Chair); Carol Baron, Ph.D. (Committee Member); James McMillan, Ph.D. (Committee Member); Thomas Good, Ph.D. (Other)

Subjects:

Education; Educational Evaluation; Educational Leadership; Elementary Education; School Administration; Teaching

Keywords:

exploratory factor analysis; confirmatory factor analysis; scale development; elementary teachers; formative assessment; formative teacher assessment; professional development; student teacher relationships; classroom environment; teacher attitudes

Gregory, Dennis KThe Development of an Instrument to Assess Students' Perceptions of Quality of Social Media Practices During the Admissions Cycle
PHD, Kent State University, 2018, College and Graduate School of Education, Health and Human Services / School of Foundations, Leadership and Administration
The purpose of this study was to develop an instrument for higher education administrators to assess their social media practices during the admissions cycle. The instrument collects data from students on their perceptions about the quality of the institution’s social media activities. A review of relevant literature was completed, and experts were consulted to develop an instrument. The instrument was distributed to 2,000 students at three different four-year public institutions for a total of 6,000. Response rates differed by institution with the highest at 19% and the lowest 6.4%. Exploratory Factor Analyses were run on the data from two of the schools. Using a replication strategy, the final model was replicated between the two EFAs. Using that model, using the data from the third sample a Confirmatory Factor Analysis was performed, also confirming that the data supported the model from the EFA. The data showed that social media was not influential in the college choice process. The final 12-item model also had high internal consistency reliability. The final instrument is an effective tool for administrators to assess their social media practices.

Committee:

Erica Eckert (Committee Co-Chair); Stephen Thomas (Committee Co-Chair); Aryn Karpinski (Committee Member)

Subjects:

Education Policy; Educational Technology; Higher Education; Higher Education Administration; Technology

Keywords:

higher education; social media; Facebook; Snapchat; Twitter; Instagram; admissions; college choice; Exploratory Factor Analysis; Confirmatory Factor Analysis; instrument creation

Carroll, Robert MorrisonA Monte Carlo comparison of nonmetric multidimensional scaling and factor analysis /
Doctor of Philosophy, The Ohio State University, 1969, Graduate School

Committee:

Not Provided (Other)

Subjects:

Psychology

Keywords:

Factor analysis;Multidimensional scaling;Monte Carlo method

Biehn, Teresa L.Examining the Underlying Dimensions of Posttraumatic Stress Disorder and Major Depressive Disorder Using the Proposed DSM-5 Diagnostic Criteria
Doctor of Philosophy, University of Toledo, 2014, Psychology
This study examined the relationship between the underlying factors of major depressive disorder (MDD) and the revised diagnostic symptom criteria of posttraumatic stress disorder (PTSD) for the fifth edition of the Diagnostic and Statistical Manual (DSM-5). Additionally, this study investigated the goodness-of-fit of the PTSD model proposed for DSM-5 and tested a model alteration which included a dysphoria factor. A total of 266 University of Toledo college students with a trauma history participated in the study. Subjects completed a modified version of the Stressful Life Events Screening Questionnaire to assess for trauma exposure which is consistent with the DSM-5’s diagnostic criteria for trauma exposure. In addition, subjects completed the PTSD Checklist (PCL) modified for the DSM-5 diagnostic criteria, and the Patient Health Questionnaire-9 (PHQ-9) for assessing depression. Confirmatory factor analyses were conducted to evaluate the goodness-of-fit of the DSM-5 PTSD model and the dysphoria model, as well as a depression model using the PHQ-9, and a combined PTSD-MDD model. Results indicate that all four models demonstrate adequate to excellent fit. The proposed DSM-5 PTSD model demonstrated superior fit over the DSM-5-adapted PTSD dysphoria model. Wald’s tests of parameter constraints were used to test the relationship between PTSD’s and MDD’s factors and indicated that PTSD's negative alterations in arousal factor and avoidance factor were more strongly related to depression's somatic factor than non-somatic factor; PTSD's negative alterations in cognitions and mood factor was more strongly related to depression's non-somatic factor than its somatic factor. This study furthers a nascent line of research examining the relationship between PTSD’s and MDD’s factors in order to better understand the nature of the high comorbidity rates between the two disorders and provides an initial analysis of the new diagnostic criteria for PTSD.

Committee:

Jon Elhai, Ph.D. (Committee Chair); Laura Seligman, Ph.D. (Committee Member); Jason Rose, Ph.D. (Committee Member); Marijo Tamburrino, M.D. (Committee Member); Scott Molitor, Ph.D. (Committee Member)

Subjects:

Clinical Psychology

Keywords:

PTSD; MDD; DSM-5; confirmatory factor analysis

Anderson, Cory AlexanderTheoretical Implications of the Beachy Amish-Mennonites
Doctor of Philosophy, The Ohio State University, 2014, Rural Sociology
One of the hallmarks of social science is the interaction of theory and methods/data, the former guiding the latter and the latter refining the former, in a cyclical relationship. The goal of theory is to provide explanations for and even predict a range of human behaviors. One potential cause of theoretical stagnation is an over focus on a singular, usually easily accessible group. Given the persistence of plain Anabaptists like the Amish as a highly distinct subgroup in American society, their utility for refining sociological theories is persuasive, but has rarely been employed to this end because of their social inaccessibility, shyness towards social science research, and the popular interpretive frames placed on them that distract would-be investigators. Even with Amish-focused scholarship, the emphasis has been largely on describing the population or applying theory to understand the Amish case, but not returning findings back to theory in critique and revision. This dissertation introduces and contextualizes the plain Anabaptists, then describes the Beachy Amish-Mennonites, a group within the Amish religious tension, but dealing markedly with tensions between separatism and assimilation. Following this introduction are three independent studies that demonstrate the use of plain Anabaptists to refine theory. The first study focuses on migration motivations. Rational choice theory is the dominant perspective in understanding migration causation: actors migrate to achieve personal ends at as low a cost as possible. Some migration may be motivated by values, such as religiously based migration. This study proposes a theory of religiously motivated migration. Inasmuch as values are derived from groups, religions with strong membership cohesion must maintain this cohesion in the face of emigration so members continue acting on value-based demands. Religious cohesion is maintained through community-level migration and affiliation-level networks, which both provide members with unbroken religious systemic integration after emigration. Three religious reasons for migration are identified: sacred command, context conducive for religious practice, and awareness of potential membership losses from religious competition. This theory is demonstrated through the case of domestic and international Amish-Mennonite migration. The second study focuses on subgroup tensions over assimilation. While numerous ethnic groups have assimilated into the American mainstream, the Amish church has embraced cultural and structural separatism on religious grounds. Elements of their cultural system are not just demarcations of social identity but direct members’ social ties, values, and interests inward, permitting the perpetuation of group socialization. However, some members may perceive a level of assimilation desirable and so pursue structural power and mobilization of external cultural resources. Because structural and cultural assimilation reinforce one another, when one weakens, the other may follow and further weaken the first. Separatist-assimilationist conflicts have dotted Amish history, most notably when progressively-oriented Amish-Mennonites have withdrawn from the Old Order Amish. While two past Amish-Mennonite movements assimilated over several generations, the most recent movement, the Beachy Amish-Mennonites, still retain a partially separate identity, though with some difficulty. Inasmuch as separatism must be maintained across generations, the orientation of Beachy young adults is of particular interest. This study investigates the social structure of a Beachy young adult network to determine what kinds of people occupy positions of power and its implications for assimilation of a third Amish-Mennonite movement. The results indicate that those who attempt to alter the content of, rather than replace and negate, separatist practices occupy positions of power, suggesting a third actor type in the separatist-assimilation conflict: revisionists. The third study focuses on mainstream Americans seeking to join the plain Anabaptists. For all the liberties granted Westerners, a small but regular stream of people seek to join seemingly austere plain Anabaptist sects (Amish, Mennonites, etc.). What are these “outsiders” seeking? I developed a survey to explore this question and posted it on a prominent Anabaptist website, offering outside seekers information about nearby churches in exchange for their time. Usable responses numbered 1,074 over two years. Evangelicals, Baptists, females, people in the Midwest and South, and the young were overrepresented. Strongest attractions include devout Christianity, strong community, and modesty. A factor analysis of 17 sources of information suggests groupings by mediated and direct information sources. A factor analysis of 21 attractions suggests six types of seeker interest, characterized by emphases on family, femininity, religious conviction, primitivism, social support, and returning to the group. Relationships between the six attraction factors and information sources, age and gender, U.S. region, and religious background and explored through regression analyses

Committee:

Joseph Donnermeyer (Committee Chair); Richard Moore (Committee Member); Richard Crenshaw (Committee Member)

Subjects:

Religion; Sociology

Keywords:

Beachy Amish-Mennonite; religious migration; social networks; religious switching; plain Anabaptists; value rational; assimilation; network power; separatism; rural; nostalgia; factor analysis; religious sect

Ransom, James AnthonyThe Role of Agency in Community Health Outcomes: Local Health Departments and Childhood Immunization Coverage Rates
Ph.D., Antioch University, 2013, Leadership and Change
Organizational culture is defined as a system of shared meaning held by members of an organization that distinguishes it from other organizations. How organizational culture is experienced in the public sector, particularly local health departments (LHDs), is not well understood. The purpose of this study was to determine whether LHD organizational culture impacts childhood immunization coverage rates. I used a modified organizational culture survey tool, the Organizational Management Survey, to quantify organizational culture and determine whether an LHD's organizational culture helps explain variations in childhood immunization coverage rates. In addition, qualitative data from an earlier study of LHD immunization staff were used to enhance the quantitative results. I used factor analysis and hierarchical regression analyses to explore organizational and demographic factors associated with variations in community childhood immunization coverage rates. The factors included organizational culture, organizational leadership, type of LHD, agency size, jurisdiction type, and participation in an immunization coalition. Among the LHD immunization programs in the study sample, organizational culture and type of LHD were significant predictors of immunization rate variation. This two-item model explained 6% of the variation in vaccination coverage levels among the respondents. The other variables did not contribute significantly. This study identified key issues for better understanding how organizational culture functions in LHDs. This research provides information on the impact that organizational culture has on work method and outcomes. Some specific changes can take place or be implemented once this is understood. The electronic version of this Dissertation is at OhioLink ETD Center, www.ohiolink.edu/etd

Committee:

Philomena Essed, PhD (Committee Chair); Carol Baron, PhD (Committee Member); Mitchell Kusy, PhD (Committee Chair); Angela Snyder, PhD, MPH (Other)

Subjects:

Health; Management; Organization Theory; Organizational Behavior; Public Health

Keywords:

Immunization Coverage, Local Health Departments, Organizational Culture, Organizational Leadership, Regression Analysis, Factor Analysis, SPSS, Organizational Management Survey, Public Health

KOSHELEVA, TATIANAINDUSTRY CLUSTERS AND METHODS OF THEIR IDENTIFICATION: APPLICATION TO THE GARY - CHICAGO REGION
MCP, University of Cincinnati, 2005, Design, Architecture, Art and Planning : Community Planning
The thesis provides a description and classification of existing theories and methods of industry cluster identification. It also critiques the applicability of some of the methods that are widely used to identify industry clusters. Then, it gives a systematical description and assessment of quantitative methods based on input-output data that are the most applicable for industry cluster identification. These methods include Factor Analysis/Principal Components Analysis, Cluster Analysis, and Graph Theoretic Analysis. Principal Components Analysis and Hierarchical Agglomerative Cluster Analysis methods were tested with 2001 NAICS-based input-output data for the Gary-Chicago five-county region. These methods were then evaluated by comparing the results of the analyses. Several variations of data inputs and variations of methods’ algorithms were applied to evaluate sensitivity and consistency of the methods. The thesis includes a detailed description of the algorithms and the step-by-step procedures for each of the methods.

Committee:

Michael Romanos (Advisor)

Keywords:

industry cluster; input-output; economic development; factor analysis; cluster analysis; graph theoretic analysis

Butler, Jamiylah YasmineSelf-Perceived Spiritual Competence of Mental Health Professionals
Doctor of Philosophy, The Ohio State University, 2010, EDU Physical Activity and Educational Services

This study investigated the five scales of the Spirituality in Counselor Education and Training Survey (West, 2007). A confirmatory factor analysis was performed on the instrument via structural equation modeling. Further, the spiritual competence of mental health professionals was assessed with this particular instrument and a demographic questionnaire. Additionally, the relationship between spiritual competence and training and education, when participants demographic characteristic were taken into consideration, was examined. A census sample was utilized from American Counseling Association members of the Association for Multicultural Counseling and Development and the Association for Spiritual, Ethical, and Religious Values in Counseling participated in the study (n=367).

The respondents ranged in age from 21 – 78 years old, with an average age of 48 years old. The majority of the sample was female (64.3%). There were 201 participants who possessed master’s degrees and 117 participants who had doctorates. The majority of the study’s participants (40.9%) were currently working as community counselors. Of the participants, approximately 19% were working in community agencies and private practice, respectively, while 28% were working in an academic environment.

Over 60% of the participants had not taken any courses with a focus on spirituality whereas 31% had between one and six courses spirituality focused courses. The mean number of courses taken with spirituality as a focus was 2.10 and those courses taken with a spirituality focus ranged from 0 – 48. Further, the study’s participants had completed 0 – 60 courses infused with spirituality with a mean of 4.38. Of the participants, 189 had not acquired any training hours after completing their counseling degree programs. The mean number of development hours obtained was 26.56 and there were 15 participants who had over 100 development hours. Toward this end, the sample was overwhelmingly religious and/or spiritual as only 9% of the population reported that they were not religious and/or spiritual. Overall, the sample believed they were spiritually competent. The implications of these results were discussed.

Committee:

James Moore, III, PhD (Committee Chair); Dorinda Gallant, PhD (Committee Member); Korie Edwards, PhD (Committee Member)

Subjects:

Psychotherapy

Keywords:

spiritual competence; spirituality; counseling; confirmatory factor analysis; structural equation modeling

Merkle, Edgar C.Bayesian estimation of factor analysis models with incomplete data
Doctor of Philosophy, The Ohio State University, 2005, Psychology
Missing data are problematic for many statistical analyses, factor analysis included. Because factor analysis is widely used by applied social scientists, it is of interest to develop accurate, general-purpose methods for the handling of missing data in factor analysis. While a number of such missing data methods have been proposed, each individual method has its weaknesses. For example, difficulty in obtaining test statistics of overall model fit and reliance on asymptotic results for standard errors of parameter estimates are two weaknesses of previously-proposed methods. As an alternative to other general-purpose missing data methods, I develop Bayesian missing data methods specific to factor analysis. Novel to the social sciences, these Bayesian methods resolve many of the other missing data methods' weaknesses and yield accurate results in a variety of contexts. This dissertation details Bayesian factor analysis, the proposed Bayesian missing data methods, and the computation required for these methods. Data examples are also provided.

Committee:

Trisha Van Zandt (Advisor)

Keywords:

Bayesian computation; Factor analysis; Missing data; Incomplete data; Data augmentation; Multiple imputation

Ayr, Lauren KDimensions of post-concussive symptoms in children with mild traumatic brain injury
Doctor of Philosophy, The Ohio State University, 2007, Psychology
The dimensions of post-concussive symptoms (PCS) associated with pediatric mild traumatic head injuries (mild TBI) were examined in a prospective, longitudinal study of 186 8- to 15-year-old children with MHI and a comparison group of 99 children with orthopedic injuries (OI). Parents and children completed a 50-item questionnaire within 2 weeks of injury and again at 3 months post injury, rating the frequency of PCS on a 4-point scale. Common factor analysis with target rotation was used to rotate the ratings to four hypothesized dimensions, representing cognitive, somatic, emotional, and behavioral symptoms. The rotated factor matrix for baseline parent ratings was consistent with the target matrix. The rotated matrix for baseline child ratings was consistent with the target matrix for cognitive and somatic symptoms but not for emotional and behavioral symptoms. The rotated matrices for ratings obtained 3 months post injury were largely consistent with the target matrix derived from analyses of baseline ratings, except that parent ratings of behavioral symptoms did not cluster as before. Additional exploratory analyses comparing younger children to older children revealed similar results to the total group for both child-rated and parent-rated symptoms. Injury group exploratory analyses suggested that child- and parent-rated symptom dimensions may be different for the OI group than the mild TBI group. Parent and child ratings of PCS yield consistent factors reflecting cognitive and somatic symptom dimensions, but dimensions of emotional and behavioral symptoms are less robust across time and raters.

Committee:

Keith Yeates (Advisor)

Subjects:

Psychology, Clinical

Keywords:

traumatic brain injury; mild trauamtic brain injury; pediatric brain injury; factor analysis

Kandula, Uday BhaskarDO THE CAUSES OF POVERTY VARY BY NEIGHBORHOOD TYPE?
Doctor of Philosophy in Urban Studies and Public Affairs, Cleveland State University, 2012, Maxine Goodman Levin College of Urban Affairs
Increasing our understanding about the nature of poverty is important due to its severe consequences at the individual, neighborhood and community levels. The purpose of this dissertation is to understand whether, or the degree to which, the causes of poverty vary across different types of neighborhoods. To accomplish this goal, cluster analysis was used to identify unique types of metropolitan neighborhoods. Next, variables that correspond to the causes of poverty were identified and entered into a factor analysis. The resulting factors were used as explanatory variables in a regression analysis explaining the variation in poverty across the different types of metropolitan neighborhoods. Findings indicate that poverty causes do vary significantly by neighborhood type. The findings can help policy makers formulate targeted neighborhood level anti-poverty strategies for the optimal utilization of limited resources.

Committee:

Brian Mikelbank, PhD (Committee Chair); Sugie Lee, PhD (Committee Member); Murali Nair, PhD (Committee Member)

Subjects:

Public Policy; Social Research; Statistics

Keywords:

"Poverty Causes; Neighborhood Types; Cluster Analysis; Factor Analysis; Geography Types; Post-Hoc Test"

Johnstone, David WestonDrinking Water Disinfection Byproduct Formation Assessment Using Natural Organic Matter Fractionation and Excitation Emission Matrices
Doctor of Philosophy, University of Akron, 2009, Civil Engineering
Disinfection byproducts (DBP) pose a major problem for the drinking water industry due to their carcinogenic nature and formation when natural organic matter (NOM) reacts with chlorine. This study investigates the formation of individual DBP compounds within waters containing various NOM characteristics. Water from the Iowa River was concentrated through reverse osmosis and NOM fractions were isolated using resin separation. In addition, waters from the city of Barberton water treatment plant were collected prior to and subsequent to coagulation. Experiments were conducted on each water source under variable chlorine doses and pH, with and without the presence of model iron oxides. The purpose of this study was to investigate the role of NOM and the surrounding environment on DBP formation and develop measures for the prediction of byproduct formation. Fluorescence excitation-emission matrices (EEM) of NOM were quantified and characterized using fluorescence regional integration (FRI) and parallel factor analysis (PARAFAC). Changes in FRI of five operationally defined regions coupled with chlorine consumption showed strong linear relationships to the formation of chloroform (CHCl3), dichloroacetic acid (Cl2AA), and trichloroacetic acid (Cl3AA). Stepwise regression of fluorescence regions revealed the use of only one region coupled with chlorine consumption to predict DBP formation, yet this region varied depending upon the individual compound assessed. This technique provides an effective tool that can utilize both chlorine reactivity and functional group properties of the NOM to predict DBP formation. PARAFAC analysis of EEM yielded three statistically significant components providing relative concentrations of fluorophores within each sample. While this technique has previously been used for NOM characterization, it has yet to be utilized to assess DBP formation. Multi-factor linear regression of select component scores showed strong linear relationships to individual DBP compounds providing insight to organic compound characteristics responsible for DBP formation. These finding suggest that fluorophore component scores may be an effective parameter used to estimate DBP precursor concentration. In doing so, water plants can evaluate the fluorescence components and assess the effects of various treatment schemes on NOM, providing a more specific approach to precursor removal and a better understanding of DBP formation.

Committee:

Christopher Miller, PhD (Advisor)

Subjects:

Civil Engineering; Environmental Engineering

Keywords:

parallel factor analysis (PARAFAC); Fluorescence EEM; DBP Formation; Chlorine

Sun, FangfangOn A-optimal Designs for Discrete Choice Experiments and Sensitivity Analysis for Computer Experiments
Doctor of Philosophy, The Ohio State University, 2012, Statistics

The first part of this dissertation is on A-optimal designs for stated choice experiments. Stated choice experiments are widely used in areas such as marketing, planning, transportation, medical care, etc. In such studies, a set of $n$ choice sets is presented to the subjects. Each choice set consists of two or more profiles. Subjects are asked to choose their favorite profile from each choice set. Therefore the outcomes of such studies are discrete and nonlinear models are usually used. The multinomial logit model (MNL) is one of the most frequently used models for stated choice experiments. There are discussions in literature about how to generate optimal designs with the MNL model but primarily with the assumption that all profiles are equally attractive.

In this dissertation, a new approach is proposed to generate A-optimal designs by the local linearization of the MNL model. Under the assumption that all options are equally attractive, this approach gives the same A-optimal designs as in the literature under the same setting but in a wider class of designs. This approach is also extendable to more general settings when profiles are unequally attractive.

The second part of this dissertation deals with sensitivity analysis for computer experiments. Sensitivity analysis is widely used for identifying influential input variables. Two approaches to evaluating sensitivity statistically are (1) estimating global sensitivity indices based on Sobol' variance decomposition, and (2) evaluating local sensitivity indices based on a gradient measure using a one-at-a-time sampling design. Although both approaches have been studied for (hyper-) rectangular input regions, they have not been considered carefully for the non-rectangular input region setting.

In this dissertation, a more flexible gradient-based method is proposed to evaluate sensitivity indices for non-rectangular regions. In addition, the use of variable-length gradients is introduced and the importance of the starting design is emphasized. It is shown by examples that the proposed method works well in both the standard and non-rectangular settings.

Committee:

Angela Dean (Committee Co-Chair); Thomas Santner (Committee Co-Chair); William Notz (Committee Member)

Subjects:

Statistics

Keywords:

A-optimal designs; discrete choice experiment; factor analysis; computer experiment; sensitivity analysis

Miraldi, Peter NelloInfluence of College Students’ MP3-Player Motives on Their Social Interaction
PHD, Kent State University, 2010, College of Communication and Information / School of Communication Studies
Despite college students’ widespread use of portable MP3 players, personal stereo research has been lacking and, thus, our understanding of MP3-player use has been limited. Furthermore, some critics have raised concern that listening to music on MP3 players is displacing users’ social interaction. However, some reports have suggested that MP3-player use can facilitate some types of social interaction. I examined college students’ MP3-player use and social interaction to address the aforementioned criticisms and to bolster our understanding of the process and outcomes of MP3-player-music listening. Uses and gratifications theory guided my study because it explains how people’s background characteristics, reasons for using media, media exposure, and activity with media content work together to influence subsequent behavior. Specifically, I examined some relationships among college students’ loneliness, motives to listen to music on an MP3 player, time spent listening to MP3-player music, activity (i.e., attention and elaboration) with MP3-player music, and four types of social interaction (i.e., time spent socializing, participation in social activities, post-listening discussion of music, and music file-sharing). Based on uses and gratifications theory, I developed research questions and hypotheses regarding college students’ MP3-player use and social interaction. A principal component factor analysis revealed seven reasons college students listened to MP3-player music: entertainment/relaxation; boredom alleviation; companionship; social utility; learning; social avoidance; and fashion/status. Partial correlations, controlling for students’ age, gender, grade level, household income, and number of roommates, were used to examine some relationships among background characteristics, MP3-player-use motives, time spent listening, activity with MP3-player music, and some types of social interaction. Students’ time spent listening to MP3-player music, attention to music, and elaboration on songs related positively to post-listening discussion of music and file-sharing. Hierarchical multiple regressions were used to examine the influence of antecedent variables on some types of social interaction. Background characteristics, including demographics and loneliness, were the strongest predictors of time spent socializing and participation in social activities. MP3-player-use motives were the strongest predictors of post-listening discussion of music and file-sharing. Overall, the findings suggest that MP3-player use facilitated some types of social interaction and did not displace social interaction as some critics had suggested.

Committee:

Paul Haridakis, PhD (Advisor); Danielle Coombs, PhD (Committee Member); Janet R. Meyer, PhD (Committee Member); Stanley T. Wearden, PhD (Committee Member)

Subjects:

Communication; Mass Media; Music

Keywords:

MP3; College Students; Uses and Gratifications; Motives; Motivation; Social Interaction; Loneliness; Exposure; Audience Activity; Attention; Elaboration; Music Listening; Portable; iPod; Partial Correlation; Regression; Factor Analysis; File Sharing

Norris, MeganExamining the Autism Phenotype: The Structure of Autism Spectrum Disorders as Measured by the Autism Diagnostic Observation Schedule
Doctor of Philosophy, The Ohio State University, 2010, Psychology
Autism spectrum disorders (ASDs) are widely studied yet poorly understood. They are characterized by impairments in social and communication skills and the presence of repetitive and stereotyped behaviors and/or circumscribed interests (RRBs). Much recent attention has been directed towards elucidating the structure of autistic symptoms. A better understanding of the phenotype can lead to improved diagnoses and clarification of etiology and pathogenesis. Factor analytic studies are one way researchers have pursued this end. Most often, two- or three-factor solutions have been reported. The objective of the current study was to test several competing models of the autism phenotype using the Autism Diagnostic Observation Schedule (ADOS). Participants included individuals with ASDs aged 3-18 years (N = 1,409) from the Autism Genetic Resource Exchange database. ADOS data from 720 participants for Module 1 and 689 participants for Module 3 were used in analyses. Samples were divided into more homogenous subgroups to examine the impact of age and level of functioning on model fit. Confirmatory factor analyses (CFAs) were performed on total samples and subsamples. Four primary models were tested: (a) a one-factor model; (b) a two-factor model (one factor consisting of social/ communication items and the other consisting of RRBs); (c) a three-factor model based on DSM-IV-TR criteria (social, communication, and RRB factors); and (d) a two-factor model based on proposed DSM-V criteria (one factor consisting of social/ communication symptoms and one factor consisting of restricted and repetitive behaviors and language). Additionally, ADI-R RRB items were added to analyses because these symptoms may not be well captured with the ADOS. Bi-factor models were also examined for the DSM-IV analyses in order to examine the possibility that ASD symptoms were best explained by one general ASD factor and three specific factors. Results of the CFAs with Module 1 indicated all models fit reasonably well, with RMSEAs ranging from .056 (DSM-IV model) to .062 (one-factor and two-factor models). RMSEA confidence intervals overlapped, suggesting no model fit significantly better than other models. Generally, fit improved in the analyses with more homogenous subgroups. Addition of ADI-R RRB items resulted in un-interpretable results. Results of the CFAs with Module 3 indicated unacceptable fit for most models, with RMSEAs ranging from .074 (DSM-V) to .083 (one-factor model). RMSEA confidence intervals again overlapped, indicating all models fit similarly. Unlike Module 1 analyses, indices of fit improved when ADI-R RRB items were included in analyses, but there was again little differentiation between models. Fit improved in the analyses with more homogenous subgroups by age, but not level of functioning. Finally, the bi-factor DSM-IV model did not aide interpretation in either module. The lack of differentiation between models in both modules suggests that the structure of ASD symptoms is complex and several research methods will be necessary to understand the symptom structure. It may also help explain why different solutions are found across studies; that is, models are similar to each other and different fit indices are found with different subgroups.

Committee:

Luc Lecavalier, PhD (Advisor); Michael Aman, PhD (Committee Member); Michael Edwards, PhD (Committee Member); Susan Havercamp, PhD (Committee Member)

Subjects:

Psychology

Keywords:

autism; factor analysis

Jackson, Patrick EEXAMINING CAMPUS AND STUDENT FACTORS THAT PREDICTED ACADEMIC PERFORMANCE AND INTENTION TO PERSIST FOR SUCCESSFUL AFRICAN AMERICAN AND LATINO STUDENTS AT FOUR-YEAR COLLEGES.
PHD, Kent State University, 2014, College and Graduate School of Education, Health and Human Services / School of Foundations, Leadership and Administration
This study examined the relationship of campus climate, institutional satisfaction, and academic adjustment in contributing to the academic performance and intentions to persist in college for successful African American and Latino students at traditional four-year colleges. Despite the dramatic increased enrollment of students of color in higher education, colleges’ strategies have failed to effectively and meaningfully increase the graduation rates for African American and Latino students (NCES, 2011). A national sample of responses on the Your First College Year survey (N = 5,559) was analyzed to describe the experiences and variables that contributed to perceptions of college campuses and academic outcomes for African American and Latino students. Methods included Exploratory Factor Analysis, Linear Regression Analysis, and Logistic Regression Analysis. Results identified the significance of: (a) Felt Discrimination on Campus; (b) Academic Self-Efficacy; (c) Sense of Belonging; and (d) Institutional Satisfaction on the academic performance and intentions to persist for respondents. This research is extremely timely because the outcry for more U.S. citizens with college credentials must include educational attainment for greater numbers of African American and Latino college students. Conclusions of this study suggest that colleges must understand and accept: (a) the needs of its changing demographics; (b) that African American and Latino students have unique needs; and (c) addressing those needs and expectations will increase student satisfaction, academic performance, and retention. Furthermore, discrimination continues to be pervasive on college campuses. Genuinely combating micro-aggressions on campus is essential to fostering a sense of belonging for students of color.

Committee:

Mark Kretovics (Committee Chair); Susan Iverson (Committee Member); Aryn Karpinski (Committee Member)

Subjects:

Academic Guidance Counseling; African American Studies; Black Studies; Continuing Education; Counseling Education; Demographics; Demography; Education; Educational Leadership; Higher Education; Higher Education Administration; Hispanic American Studies; Hispanic Americans; Multicultural Education; Social Research

Keywords:

African American; Black; Hispanic; Latino; college student; persistence; retention; academic performance; factor analysis; regression analysis; campus climate; institutional satisfaction; academic self-efficacy; sense of belonging; discrimination

Zhang, YuleiComputer Experiments with Both Quantitative and Qualitative Inputs
Doctor of Philosophy, The Ohio State University, 2014, Statistics
Physical experiments play an important role in agriculture, industry, and medical research. However, physical experiments can sometimes be difficult or even impossible to run. In these situations, computer experiments are becoming desirable surrogates for physical experiments. This dissertation considers designs and the predictive models for computer experiments with both quantitative and qualitative input variables. The existing framework for building Gaussian stochastic process (GaSP) models with quantitative and qualitative inputs is to treat a given set of values of the qualitative inputs as determining a response surface in the qualitative inputs. A GaSP model is assumed for each of these response surfaces and the same covariance structure is used for each response surface. A cross-correlation parameter is introduced for each pair of sets of values of the qualitative variables in order to "capture" correlations between response surfaces. To guarantee that one has a legitimate overall covariance structure, certain conditions are imposed on the cross-correlation parameters. In the first part of this dissertation, we introduce two indicator-based GaSP models by transforming the qualitative inputs into quantitative variables and then use traditional correlation functions for quantitative inputs. We also show the equivalence properties between these new models and the existing model. The second part of this dissertation is about the experimental designs with both quantitative and qualitative inputs. The special data structure requires that a "good" design not only capture the cross-correlation information but also spread observations out over the entire quantitative inputs space. We propose two types of designs, the partial SLHD and partial CSLHD, which are modifications of existing designs in the literature, and compare their prediction accuracy with all the other existing designs for quantitative and qualitative. By examining several examples, we find that what constitutes a "good" design may vary from case to case. We summarize these findings with a "guideline" for selecting initial designs. Furthermore, when the initial design does not perform well, we also propose a sequential design algorithm to interpolate or extrapolate the target response levels in a GaSP model with mixed inputs. Inspired by factor analysis, in the last part of this dissertation, we build a more general composite covariance structure by converting the GaSP model with several qualitative levels into a linear combination of independent stochastic processes with fewer constraints on the variance and correlation functions. Furthermore, this composite covariance structure can be extended to the case with multiple qualitative inputs. In these cases, we introduced the Kronecker product form of the composite covariance function, which can not only reduce the number of the parameters, but also capture the similarity between different qualitative inputs with some identical components. In addition, we propose an ANOVA decomposition form of the Gaussian processes, which imposes a factorial structure on the response outputs. Finally, we extend the sequential design algorithm to the composite GaSP model.

Committee:

William Notz (Advisor); Peter Craigmile (Committee Member); Matthew Pratola (Committee Member)

Subjects:

Statistics

Keywords:

Computer Experiments; Physical Experiments; Gaussian Stochastic Process Model; Quantitative and Qualitative Inputs; Cross-Correlation Parameters; Experimental Designs; Composite GaSP Model; Factor Analysis; Kronecker Product; ANOVA Decomposition

Oet, Mikhail VFinancial stress in an adaptive system: From empirical validity to theoretical foundations
Doctor of Philosophy, Case Western Reserve University, 2016, Management
A review of financial system stress measures reveals not only the absence of theory on financial stress, but also the absence of search for theory. To remedy this gap, this study conducts a rigorous investigation of the empirical validity and dynamic properties of financial stress measurement in the context of financial system complexity. We provide and validate four contributions to literature. First, we establish the relevance and comparative quality of macro-level stress measurement for the financial system relative to alternative measures of system conditions. Second, we establish theoretical foundations for measuring financial stress across multiple units of analysis. This measure builds on the understanding of stress origins and drivers and incorporates price, quantity, and behavioral variables to explain the pattern of apparently irrational choices of financial agents. At the macro-level, stress is supported empirically by hypotheses of association between behavioral aspects of heterogeneous financial agents and overall financial system stress. At the micro-level, we apply abductive inference to the empirical results to propose a new theoretical stress measure for heterogeneous agents and instruments. Defining financial stress theoretically allows continual measurement of financial stress at the level of the various heterogeneous partitions of the financial system (e.g. agents and instruments) as these partitions evolve through structural changes and financial innovations. Third, we build a theory of stress transmission across micro-level of sectoral agents to the macro-level of the financial system. This theory describes a process of stress transmission across financial intermediaries and the process by which its agent stress escalates to the financial system. Fourth, we examine the process by which unusual conditions in the financial markets manifest as critical states of financial system stress.

Committee:

Kalle Lyytinen (Committee Chair); Lucia Alessi (Committee Member); Agostino Capponi (Committee Member); Myong-Hun Chang (Committee Member); Corinne Coen (Committee Member)

Subjects:

Banking; Economics; Finance; Management

Keywords:

financial stress; heterogeneous agents; empirical validity; factor analysis; dynamic factors, stochastic analysis; content analysis

Pohlen, Michael FrankA factor analytic approach to weapon system analysis /
Doctor of Philosophy, The Ohio State University, 1967, Graduate School

Committee:

Not Provided (Other)

Subjects:

Business Administration

Keywords:

Weapons systems;Weapons systems;Factor analysis

Brett, William AllenA factorial study of the items in a mathematics placement test /
Doctor of Philosophy, The Ohio State University, 1954, Graduate School

Committee:

Not Provided (Other)

Subjects:

Psychology

Keywords:

Ability;Factor analysis;College entrance achievement tests;Mathematics

Next Page