This research investigated the association of street network connectivity differences across travel modes with travel behaviour – mode choice, distance traveled and number of trips. To date research on travel behaviour relationships with urban form has not developed empirical evidence on street designs as distinct networks for walking and driving. A street network having greater connectivity and continuity for the pedestrian mode of travel vis-à-vis the vehicular network, like the Fused Grid, will likely encourage more walking. This hypothesis was investigated using a quasi-experimental approach within a rational utility behavioural framework. Local travel behaviour is theorized to be affected by desire to access goods and services (broadly termed, ‘activities’) in the community where people live. Using inferential statistics, the research tested for relationships between measured street patterns and self-reported local travel by King County, WA households. The main variables were ratios (walking : driving) of network connectivity and density, in the vicinity of travel survey households. Demographics and household characteristics, as well as other behaviourally influential urban form factors (residential density, proximity of destinations, etc.), were included in regression models, allowing control for confounding factors. Findings suggest that street networks with connectivity that provides better routing for one mode of transportation over others encourage more travel by the favored mode. The regression model demonstrated that a change from a pure small-block grid to a modified grid (i.e. Fused Grid) can result in an 11.3% increase in odds of a home-based trip being walked. The modified street pattern like a Fused Grid is also associated with a 25.9% increase, over street patterns with equivalent route directness for walking and driving, in the odds a person will meet recommended levels of physical activity. Finally, the Fused Grid’s 10% increase in relative connectivity for pedestrians is associated with a 23% decrease in local vehicle travel distance (VMT), and its improved continuity is associated with increased walking trips and distance. Conclusions: Other factors being equal, residential street networks with either more direct routing for pedestrians or more pedestrian facilities relative to vehicular network are associated with improved odds of walking and reduced odds of driving. / Applied Science, Faculty of / Community and Regional Planning (SCARP), School of / Graduate

Innovativeness is one of the fundamental instruments of growth strategies that provide companies with a competitive edge. Only a few recent studies have examined marketing innovation and the factors that might encourage its adoption. This study investigates the factors that motivate marketing innovation and examines whether the occurrence of marketing innovation varies across industry sectors. This study uses data from surveys and a nationwide census conducted by Statistics Canada. They include: the Survey of Innovation and Business Strategies (SIBS) 2009, the Survey of Innovation and Business Strategies (SIBS) 2012, the Business Registry (BR) and the General Index of Financial Information (GIFI). Multilevel (random-intercept) logistic regression modelling is employed. The results show that if a firm has a strategic focus on new marketing practices, maintains marketing within its enterprise, acquires or expands marketing capacity, has competitor and customer orientations, and adopts advanced technology then it is more likely to carry out marketing innovation. However, breadth of long-term strategic objectives and competitive intensity do not have significant impacts on marketing innovation. In addition, product innovation and organizational innovation occur simultaneously with marketing innovation, but process innovation may not. Lastly, the occurrence of marketing innovation is found to vary across industry sectors. The theoretical and empirical implications of the results are discussed within this study.

The goal of this work is to identify and analyse factors with impact on the income decrease of households under the poverty line. Data used in this work are taken from EU SILC survey. In this work is created a statistical model which help us to discover relevant and irrelevant factors. The situation and it's development is analysed only for Czech households in this work

Abstract Background - Bankruptcy is an issue that not only affects the company that is registered as bankrupt, but also the society since it has an impact on the economy. Previous studies have been focusing on larger listed companies outside of Sweden hence there is a lack of empirical findings about Swedish companies in this research area. Small and medium companies represent most of the Sweden's labor force and therefore the bankruptcy issue is important to investigate for these companies. Purpose - The purpose of the thesis is to find out which financial information distinguishes bankrupt from non-bankrupt companies in Sweden. In other words, which financial ratios have predictive power on bankruptcy. Furthermore, the thesis wants to provide knowledge towards current and future companies so that they can avoid bankruptcy by paying attention to the ratios distinguished in the thesis and keeping the ratios at an acceptable level. Method – The thesis conducts the research with a quantitative strategy by observing financial information from companies’ annual reports. The logistic regression model is used to test for the 11 ratios, by matching two samples; bankrupt and non-bankrupt companies, as well as a classification matrix, Pearson correlation matrix and variance inflation factor. The bankrupt companies selected, are classified as bankrupt for the period 2016-2019. The thesis implements a deductive approach to establish expectation and deduct which financial ratios are predictive. Conclusion - The thesis ends up with 92 companies, where 46 are bankrupt and 46 are nonbankrupt. Out of the 11 ratios, three are statistically significant and have predictive power on bankruptcy. These three are; debt rate, gross profit margin and, cash and cash equivalents. The debt rate has a positive effect on bankruptcy, which means that a higher debt rate increases the risk of bankruptcy. Gross profit margin and cash and cash equivalents have a negative effect on bankruptcy; as they increase, the risk of bankruptcy decreases.

Eligibility requirements, the pressure to remain eligible at all costs, and demanding time schedules are high stakes issues that affect the National Colligate Athletic Association (NCAA) student-athletes. A gap in research existed on whether college student-athletes’ demographics and engagement predicts their academic success. The purpose of this quantitative research was to determine the extent to which engagement and demographic factors predict student-athletes’ academic success, as measured by a self-reported grade of B or higher in NCAA first-year student-athletes. This study was influenced by Astin’s student involvement theory and Kuh’s concept of engagement. The research question guiding this study addressed the extent to which academic and cocurricular engagement, race, sport played, and gender predict NCAA student-athletes’ academic success. Quantitative data were collected from the 2018 National Survey of Student Engagement. The sample analyzed included 1,985 student-athletes. Logistic regression analysis was used to find that males, wrestlers, football players, and Black or African American student-athletes were less likely to achieve academic success, whereas females, tennis players, and both White and Asian student-athletes were more likely to achieve academic success than their peers. Findings were significant at the .05 level, but the variance explained by the models was less than 10%, which implies limited practical significance. Time spent on cocurricular activities and time spent preparing for class did not predict academic success. The findings of this study may be used by the NCAA and higher education institutions to help understand student-athletes’ behaviors and the implications for supporting academic success.

A security operation center (SOC) is a cybersecurity clearinghouse responsible for monitoring, collecting and analyzing security events from organizations’ IT infrastructure and security controls. Despite their popularity, SOCs are facing increasing challenges and pressure due to the growing volume, velocity and variety of the IT infrastructure and security data observed on a daily basis. Due to the mixed performance of current technological solutions, e.g. intrusion detection system (IDS) and security information and event management (SIEM), there is an over-reliance on manual analysis of the events by human security analysts. This creates huge backlogs and slows down considerably the resolution of critical security events. Obvious solutions include increasing the accuracy and efficiency of crucial aspects of the SOC automation workflow, such as the event classification and prioritization. In the current thesis, we present a new approach for SOC event classification and prioritization by identifying a set of new machine learning features using graph visualization and graph metrics. Using a real-world SOC dataset and by applying different machine learning classification techniques, we demonstrate empirically the benefit of using the graph-based features in terms of improved classification accuracy. Three different classification techniques are explored, namely, logistic regression, XGBoost and deep neural network (DNN). The experimental evaluation shows for the DNN, the best performing classifier, area under curve (AUC) values of 91% for the baseline feature set and 99% for the augmented feature set that includes the graph-based features, which is a net improvement of 8% in classification performance. / Graduate

Eligibility requirements, the pressure to remain eligible at all costs, and demanding time schedules are high stakes issues that affect the National Colligate Athletic Association (NCAA) student-athletes. A gap in research existed on whether college student-athletes' demographics and engagement predicts their academic success. The purpose of this quantitative research was to determine the extent to which engagement and demographic factors predict student-athletes' academic success, as measured by a self-reported grade of B or higher in NCAA first-year student-athletes. This study was influenced by Astin's student involvement theory and Kuh's concept of engagement. The research question guiding this study addressed the extent to which academic and cocurricular engagement, race, sport played, and gender predict NCAA student-athletes' academic success. Quantitative data were collected from the 2018 National Survey of Student Engagement. The sample analyzed included 1,985 student-athletes. Logistic regression analysis was used to find that males, wrestlers, football players, and Black or African American student-athletes were less likely to achieve academic success, whereas females, tennis players, and both White and Asian student-athletes were more likely to achieve academic success than their peers. Findings were significant at the .05 level, but the variance explained by the models was less than 10%, which implies limited practical significance. Time spent on cocurricular activities and time spent preparing for class did not predict academic success. The findings of this study may be used by the NCAA and higher education institutions to help understand student-athletes' behaviors and the implications for supporting academic success.

Meta-analysis refers to the quantitative synthesis of information across different studies. Since outcomes from different studies are likely to be reported in different units, study-level results are typically transformed to the same scale before quantitative integration. Typically, this leads to the accumulation and combination of effect sizes. To date, most social scientists have synthesized, or meta-analyzed, zero-order statistics like a correlation. Synthesizing partial effect sizes is an alternative which allows a meta-analysis to account for the influence of nuisance variables when estimating the association between two variables. This dissertation proposes that logistic regression coefficients from different studies, which are a type of partial effect size, can be meta-analyzed. Logistic regression models how a set of covariates relates to a binary dependent variable. Given a key independent variable (IV) of interest, which we can call the focal IV or Xf, the slope estimate (βf) in a logistic regression measures the impact of Xf on Y on the logit (log-odds) scale, while controlling for other variables. Four assumptions justify the possibility of comparing and possibly combing logistic slopes across studies: (1) Y must be on the same scale, (2) Xf must be on the same scale, (3) all effect sizes are logistic regression slopes adjusted for the same covariates, and (4) model specifications are identical. In practice, the third assumption is particularly challenging as different studies inevitably include different sets of control variables. Three simulation studies are implemented to understand how synthesizing a logistic regression slope on the logit scale is affected by several factors. Across these three simulation studies, the following meta-analytic variables are tested: (1) the size of the partial effect size (βf), (2) Study-level sample size (k), (3) Within-study sample size (N), (4) the degree of between-study variance, (5) a continuous vs. a binary focal predictor, (6) the level of collinearity between Xf and other covariates included in primary studies, (7) the magnitude of non-focal variable slopes, (8) different covariate sets used in primary-level studies, and (9) meta-analytical method. Simulation performance is based on how the bias and mean-squared error (MSE) are affected by each of these simulation parameters. Overall, results suggest that when the four assumptions introduced above are satisfied, meta-analyzing logistic regression slopes is remarkably accurate as the summary effect resulting from the standard random-effects meta-analytic model leads to small levels of bias and MSE under a variety of conditions. When the assumptions are broken (and particularly the third assumption of identical covariate sets), the pooled slope estimator can have large degrees of bias. The bias is a function of within-study sample size, between-study sample size, distribution of the focal IV (i.e., continuous vs. categorical variable), multicollinearity, the magnitude of non-focal variable slope parameters, diversity in covariate sets, and choice of meta-analytical methods. The MSE is a function of study-level sample size, within-study sample size, distribution of the focal IV (i.e., continuous vs. categorical variable), multicollinearity, the magnitude of non-focal variable slope parameters, diversity in covariate sets, and choice of meta-analytical methods. A complex four-way interaction is discovered between collinearity, the magnitude of non-focal variable slope parameters, diversity in covariate sets, and choice of meta-analytical methods. An applied example focusing on estimating the effects of albumin on mortality is also presented to complement the simulation results.

The analysis of gaining, retaining and maintaining customer trust is a highly topical issue in the e-commerce industry to mitigate the challenges of increased competition and volatile customer relationships as an effect of the increasing use of the internet to purchase goods. This study is conducted at the Swedish online fashion retailer NA-KD with the aim of gaining better insight into customer behavior that determines purchases, returns and churn. Therefore, the objectives for this study are to identify the group of loyal customers as well as construct models to predict customer loyalty, frequent returns and customer churn. Two separate approaches are used for solving the problem where a clustering model is constructed to divide the data into different customer segments that can explain customer behaviour. Then a classification model is constructed to classify the customers into the classes of churners, returners and loyal customers based on the exploratory data analysis and previous insights and knowledge from the company. By using the unsupervised machine learning method K-prototypes clustering for mixed data, six clusters are identified and defined as churned, potential, loyal customers and Brand Champions, indecisive shoppers, and high-risky churners. The supervised classification method of bias reduced binary Logistic Regression is used to classify customers into the classes of loyal customers, customers of frequent returns and churners. The final models had an accuracy of 0.68, 0.75 and 0.98 for the three separate binary classification models classifying Churners, Returners and Loyalists respectively.

Thesis advisor: Zhushan Mandy Li / Differential item functioning (DIF) occurs when examinees of equal ability from different groups have different probabilities of correctly responding to certain items. DIF analysis aims to identify potentially biased items to ensure the fairness and equity of instruments, and has become a routine procedure in developing and improving assessments. This study proposed a DIF detection method using regularization techniques, which allows for simultaneous investigation of all items on a test for both uniform and nonuniform DIF. In order to evaluate the performance of the proposed DIF detection models and understand the factors that influence the performance, comprehensive simulation studies and empirical data analyses were conducted. Under various conditions including test length, sample size, sample size ratio, percentage of DIF items, DIF type, and DIF magnitude, the operating characteristics of three kinds of regularized logistic regression models: lasso, elastic net, and adaptive lasso, each characterized by their penalty functions, were examined and compared. Selection of optimal tuning parameter was investigated using two well-known information criteria AIC and BIC, and cross-validation. The results revealed that BIC outperformed other model selection criteria, which not only flagged high-impact DIF items precisely, but also prevented over-identification of DIF items with few false alarms. Among the regularization models, the adaptive lasso model achieved superior performance than the other two models in most conditions. The performance of the regularized DIF detection model using adaptive lasso was then compared to two commonly used DIF detection approaches including the logistic regression method and the likelihood ratio test. The proposed model was applied to analyzing empirical datasets to demonstrate the applicability of the method in real settings. / Thesis (PhD) — Boston College, 2019. / Submitted to: Boston College. Lynch School of Education. / Discipline: Educational Research, Measurement and Evaluation.