Browsing by Subject "Factor analysis"
Now showing 1 - 9 of 9
- Results Per Page
- Sort Options
Item Commuter Linkages Among Counties in the Twin Cities and Greater Minnesota(1993-09) Adams, John S.; Wyly, Elvin K.The continued decentralization of metropolitan areas has replaced the well-defined daily urban systems of the 1960's with complex, overlapping commuting fields. This report analyzes county-tocounty commuting flows in Minnesota and counties in adjacent states to evaluate changes in the state's urban systems between 1960 and 1990. Findings confirm that inter-county commuting has increased dramatically, from 7% in 1960 to nearly 19% in 1990. The rate of growth is diminishing, but the total number of commuters is considerable. In 1990, over 70,000 workers commuted to the seven-county Twin Cities Metropolitan Area (TCMA) from Greater Minnesota. Results of a multivariate statistical procedure, factor analysis, confirm that exurban counties between the Twin Cities and nearby regional centers have been drawn into a complex web of interconnected, overlapping urban systems. These findings support the hypothesis that the daily work journey is creating an interdependent network of urban systems in the densely settled portions of the state. The increasing gap between the seven-county TCMA and the practical extent of the Twin Cities underscores the question whether the jurisdiction of the Metropolitan Council should expand to include counties connected by the daily flow of workers to the Twin Cities.Item Developing a self-rated instrument of work-related well-being for music therapy professionals(2008-09) Chang, Nai-WenThe purpose of this study was to design an assessment instrument of work-related well-being for music therapy professionals. An interview method was applied to construct a conceptual theory based on the data collected from seven music therapy professionals with diverse backgrounds. An on-line survey of work-related well-being, which contained 54 five points Likert-type items, was derived through analyzing the contents of the interviews. Four hundred ninety-three music therapy professionals in the US were randomly selected to participate in the survey, and 157 responded (respond rate 32 %). Among them, 117 samples were determined to be valid for use in the factor analysis. Factor analysis revealed five factors of work-related well-being for music therapy professionals, including work satisfaction, stressors, self-awareness, work demands, and self-care skills. Statistical techniques, namely Pearson correlation, independent t-test and one-way ANOVA, were used to determine the impact of work years, education levels, and salaries on perception of work-related well-being. The results showed that music therapy professionals reported satisfaction both in their overall feeling of work-related well-being and combined factor scores. Also, the combined factor scores positively correlated to overall scale of work-related well-being. The experienced music therapy professionals have significantly higher combined factor scores of work-related well-being than do novice music therapy professionals. In addition, education levels do not show statistically significant differences on the combined factor scores of work-related well-being. Finally, salary levels do not exhibit statistically significant impact on factor scores of work-related well-being, though the p-value is much smaller (p = .105). Analysis of seven interviews and psychometric methods were applied to verify the validity and reliability of the resultant assessment instrument. Suggestions for future use of the instrument are also provided.Item Job Satisfaction of Nurses in Jamaica(2013-12) Nelson, John WillardBackground: No model of nurse job satisfaction was found in the literature that had been empirically tested in Jamaica or surrounding countries in the Caribbean.Objective: The objective of this study was to test an instrument of nurse job satisfaction in Jamaica and use results to improve nurse job satisfaction at the unit level and refine efficiency of care delivery across the hospital.Methods: Convenience sampling was used to gather data in a 579-bed urban hospital in Southeast Jamaica regarding nurse job satisfaction, nurses' clarity of self, role and system, and demographics. Parceling of data was used in a confirmatory factor analysis (CFA) to test an 11-factor construct of nurse job satisfaction. Hierarchical regression was used to examine explained variance of nurse job satisfaction.Results: Complete surveys from 82 nurses (14% response rate) revealed good model fit for all 11 dimensions, including four social factors (satisfaction with relationship with coworkers, relationship with the patient, relationship with unit/ward manager, and relationship with physicians) and seven technical dimensions (satisfaction with resources, autonomy, staffing/scheduling, professional growth, executive leadership, distributive justice, and workload). Results revealed adequate fit, RMSEA .08, CFI .90, and SRMR .07. Path coefficients ranged from .35 to .72 (p = < .001 for all coefficients). The best fitting model for predicting nurse job satisfaction included service line (R = .475, R2 = .226, F (7,74) = 3.078, p = .007), and clarity of role (R = .543, R2 = .295, F (1,73) = 7.192, p = .009). Combined, both predictors explained 29.5% of the variance of nurse job satisfaction. Discussion: Data was presented to staff and management to understand the 11 dimensions of nurse job satisfaction in this sample in Jamaica. Results were presented at the aggregate hospital and unit level. Staff and management are currently using the results to make changes at the unit level, using the data to guide planning. This study met the objective to empirically develop, test, and use a model of nurse job satisfaction in Jamaica.Item Major patterns of dietary intake in adolescents: identification, stability over time, socio-demographic and socio-environmental correlates, and association with obesity.(2010-10) Cutler, Gretchen JeanPurpose: Few studies have used data-driven dietary pattern analysis in adolescents, but it can be a useful method to summarize dietary intake. This dissertation had three aims: 1) describe the major patterns of dietary intake in a cohort of ethnically and socio-economically diverse adolescents, examine the stability of these patterns over a five-year period, and study the dietary profile of the identified patterns, 2) examine the socio-demographic and socio-environmental correlates of adherence to the indentified dietary patterns with specific regard to the dietary profile of these patterns (healthier vs. unhealthy), and 3) study the relationship between adherence to these healthier and unhealthy patterns and weight status. Methods: Data from the longitudinal Project EAT (Eating Among Teens) study were used in all analyses. Project EAT-I (Time 1), collected data on 4746 middle school (younger cohort) and high school (older cohort) students during the 1998-1999 academic year. Project EAT-II (Time 2) resurveyed 53% (n=2516) of the original cohort in 2003-2004. Dietary intake was assessed using the Youth/Adolescent Food Frequency Questionnaire at both time points. Principal components factor analysis was used to identify dietary patterns at Time 1 and Time 2. Multivariable linear regression was used to examine the relationship between socio-demographic and socio-environmental characteristics and factor scores for the identified dietary patterns. Multivariable logistic regression was used to examine the relationships between scores for each dietary pattern and risk for overweight/obese weight status. All models were run separately by age cohort and gender. Results: Four dietary patterns were identified at Time 1: vegetable, fruit, starchy food (e.g., mashed potatoes, pancakes), and sweet & salty snack food. Similar patterns were identified at Time 2, with the exception of a new `fast food' pattern. Multiple socio-demographic and socio-environmental characteristics were found to be significantly associated with adherence to healthier and unhealthy patterns of dietary intake. Socio-economic status, family meal frequency, healthy home food availability, and parental and peer support for healthy eating were positively associated with adherence to the healthier patterns, and inversely associated with the unhealthy patterns. The opposite relationships were seen for availability of unhealthy food in the home. Inverse associations were seen between the healthier vegetable and fruit patterns and overweight/obese weight status in girls, while inverse associations between the unhealthy `sweet & salty snack food' pattern and overweight/obese status were found in boys. Conclusion: Dietary patterns were identified in this adolescent population that were analogous across gender and age cohorts, and were relatively similar over time, with the exception a new "fast food" pattern identified at Time 2. The nutrient profile showed that the identified dietary patterns reflect intake of important nutrients and food groups, underscoring the value of this method to summarize dietary data in adolescent populations. Multiple correlates of dietary patterns were identified in adolescents in both cross-sectional and prospective analyses, including modifiable characteristics that may be possible targets for dietary interventions. Consistent or intuitive associations were not found between dietary patterns and weight status. Identified patterns may not capture the elements of diet that are truly important in determining adolescent weight, or diet may not be the primary driver in determining weight status at this age.Item Method to adjust Institute of Transportation Engineers vehicle trip-generation estimates in smart-growth areas(Journal of Transport and Land Use, 2015) Schneider, Robert James; Shafizadeh, Kevan; Handy, Susan L.This paper describes a practical method of adjusting existing Institute of Transportation Engineers (ITE) estimates to produce more accurate estimates of motor-vehicle trip-generation at developments in smart-growth areas. Two linear regression equations, one for an A.M. peak-hour adjustment and one for a P.M. peak-hour adjustment, were developed using vehicle trip counts and easily measured site and surrounding area context variables from a sample of 50 smart-growth sites in California. Many of the contextual variables that were associated with lower vehicle trip generation at the smart-growth study sites were correlated. Therefore, variables representing characteristics such as residential population density, employment density, transit service, metered on-street parking, and building setback distance from the sidewalk were combined into a single “smart-growth factor” that was used in the linear regression equations. The A.M. peak-hour and P.M. peak-hour adjustment equations are only appropriate for planning-level analysis at sites in smart-growth areas. In addition, the method is only appropriate for single land uses in several common categories, such as office, mid- to high-density residential, restaurant, and coffee/donut shop. The method uses data from California, but the methodological approach could provide a framework for adjusting ITE trip-generation estimates in smart-growth areas throughout the United States.Item Quality of Life: Assessment for Transportation Performance Measures(Minnesota Department of Transportation, 2013-01) Schneider, Ingrid E.; Guo, Tian; Schroeder, SierraQuality of life (QOL) is a commonly used term. Defining QOL, however, is an ongoing challenge that experts often take on with minimal input from citizens. This groundbreaking research sought citizen input on what comprised QOL and what role transportation played in it. Further, this research explored in detail the important factors across the breadth of transportation and how the Minnesota Department of Transportation (MnDOT) was performing on these important factors. The research encompassed three phases between 2010 and 2011: (1) an extensive literature review on QOL, (2) 24 focus groups that asked Minnesota’s citizens about their QOL, and (3) a mail questionnaire about what matters in quality of life, transportation and their intersection. Eleven related quality of life factors emerged, including transportation: education, employment and finances, environment, housing, family, friends and neighbors, health, local amenities, recreation and entertainment, safety, spirituality/faith/serenity, and transportation. Within transportation, seven important areas were identified that predicted satisfaction with MnDOT services: access, design, environmental issues, maintenance, mobility, safety and transparency. Results reveal that a) QOL is complex and transportation plays an important and consistent role in it across Minnesota; b) transportation is critical to QOL because it connects us to important destinations in aspects that matter most; and c) Minnesotans can readily identify what matters and how the state is performing within the breadth of transportation services.Item Selected topics of high-dimensional sparse modeling(2013-11) Yi, FengIn this thesis we study three problems over high-dimensional sparse modeling. We first discuss the problem of high-dimensional covariance matrix estimation. Nowadays, massive high-dimensional data are more and more common in scientific investigations. Here we focus on one type of covariance matrices - bandable covariance matrices in which the dependence structure of variables follows a nature order. Many off-diagonal elements are very small, especially when they are far away from diagonal, which technically makes the covariance matrix very sparse. It has been shown that the tapering covariance estimator attains the optimal minimax rates of convergence for estimating large bandable covariance matrices. The estimation risk critically depends on the choice of tapering parameter. We develop a Stein's Unbiased Risk Estimation (SURE) theory for estimating the Frobenius risk of the tapering estimator. SURE tuning selects the minimizer of SURE curve as the chosen tapering parameter. Covariance matrix is finally estimated according to the selected tapering parameter in the tapering covariance estimator. The second part of the thesis is about high-dimensional varying-coefficient model. Varying-coefficient model is used when the effects of some variables depend on the values of other variables. One interesting and useful varying-coefficient model is that the coefficients of all variables are changing over time. Non-parametric method based on B-splines is used to estimate marginal coefficient of each variable, and varing-coefficient Independence Screening (VIS) is proposed to screen important variables. To improve the performance of the algorithm, Iterative VIS (IVIS) procedure is proposed. In the third part of the thesis, we study a high-dimensional extension of traditional factor analysis by relaxing the independence assumption of the error term. In the new model, we assume that the inverse covariance is sparse but not necessarily diagonal. We propose a generalized E-M algorithm to fit the extended factor analysis model. Our new model not only makes factor analysis more flexible, but also could be used to discover the hidden conditional structure of variables after common factors are discovered and removed.Item Statistical Methods for Materials Testing(Minnesota Department of Transportation, 2009-12) Gupta, Diwakar; Peterson, AmyMn/DOT provides incentives to contractors who achieve high relative density via a pay factor applied to each unit of work. To determine the pay factor, Mn/DOT divides each day of a contractor’s work into a small number of lots. Then, core samples are taken from two locations within each lot and the relative densities of the cores are calculated by performing standardized tests in materials testing laboratories. The average of these two values is used as an estimate of the lot's relative density, which determines the pay factor. This research develops two Bayesian procedures (encapsulated in computer programs) for determining the required number of samples that should be tested based on user-specified reliability metrices. The first procedure works in an offline environment where the number of tests must be known before any samples are obtained. The second procedure works in the field where the decision to continue testing is made after knowing the result of each test. The report also provides guidelines for estimating key parameters needed to implement our protocol. A comparison of the current and proposed sampling procedures showed that the recommended procedure resulted in more accurate pay factor calculations. Specifically, in an example based on historical data, the accuracy increased from 47.0% to 70.6%, where accuracy is measured by the proportion of times that the correct pay factor is identified. In monetary terms, this amounted to a change from average over and under payment of $109.60 and $287.33 per lot, to $44.50 and $90.74 per lot, respectively.Item The structure of virtue: An empirical investigation.(2009-09) Shryack, JessicaThis project is guided by the need for a common model of virtuous personality that can integrate theory and research on positive personality traits across the fields of positive psychology, personality, moral development and character education. A particular concern is that character education programs lack an empirically-based structural model of virtue - which could be provided by mainstream psychological research - even while initiatives to strengthen character in America's schools have been popular and wellfunded in the past few decades. The current project was designed to do two things: 1) examine the structural validity of a rationally-derived model of virtue in two separate factor analytic studies, and 2) relate the resulting major virtue dimensions to dimensions of normal personality and to virtue-relevant criterion variables. Specifically, in Study 1, an exploratory scale factor analysis of a popular virtues assessment (the VIA-IS) was conducted to determine the fit of different models using multiple retention criteria. In Study 2, an exploratory item factor analysis was conducted using items from the International Personality Item Pool (IPIP) to represent the VIA-IS item content domain and factors were related to measures of normal personality, altruism, academic experiences and relevant demographic variables. Evidence for a three- and five-factor structure was found, with certain factors (e.g. Temperance) replicating across Studies 1 and 2. In addition, virtues predicted variance in altruism scores over and above that provided by a measure of normal personality.