Recent literature contains many publications on techniques for identifying extreme data points (outliers) and influential observations or groups in sample data sets. This thesis begins by reviewing the statistics and distributional properties of the standard techniques, viz. the standardized residual as a test for outliers, and Cook's distance as a measure of influence. An outlier test which is distributionally neater than the standardized residual is proposed. In practical applications, ordinary least squares regression is often inappropriate, and the use of biased estimators may be preferable. In this thesis, the existing theory is extended to several alternative regression techniques. Ridge regression and generalized inverse regression are suitable techniques when the cross-product matrix is ill-conditioned. Restricted least squares regression, with exact or stochastic prior information, · is used in many econometric application~. Models with selected · variables-are used to eliminate design faults or to reduce computational effort. New statistics are developed for all these techniques, the distributional results are proved, and computational formulae are developed. Computational problems may arise in the actual use of the various techniques, and these are investigated. Computer programs written in BASIC and suitable for microcomputer use are presented, making the techniques accessible to virtually any commercial environment. The performance of the various techniques is examined, using a controlled simulation study and a number of practical data sets drawn from several areas of South African commerce. This is, as far as can be ascertained, the first extensive practical South African study on the effects of influential data. It is shown that the presence of outliers or influential data can bias the results of any study significantly. It is recommended that no data analysis should be attempted without a preliminary scan of outliers and influential observation. The techniques presented can be used advantageously even in data sets where the ultimate analysis does not involve linear regression. It is shown that influential data are not merely of nuisance value in the analysis but may contain valuable - information in their own right._

Although the strategy formation process in large companies has been extensively and deeply researched, the strategy making in SME (small and medium sized companies) is largely under-investigated by researchers. In our thesis, we find even for entrepreneurial SME owners, the process doesn’t exhibit the characteristics of comprehensive and exhaustive environmental scanning and strategic analysis. Instead, the strategy formation in entrepreneurial SMEs is a combination of systematic planning and improvisation, a combination of proactivity and reactivity. And the limited planning and proactivity is more reflected on the SME owner’s cognitive level, they are strategically aware, sensitive and flexible to any change that will affect their company and immediately know the relevant implications. Our finding is in line with Mintzberg’s insightful notion that “strategy as a pattern” and “strategic thinking”. The SME owner’s opportunistic, intuitive and emergent approach to strategy making often involves more than themselves. Families, friends, company board of directors, accountants, consultants are also influential actors participating and contributing to this process in different ways.

There is a lack of information on influential Appaloosa stallions from the 1960s to present day. Appaloosa Horse Club members participated in a survey to identify which Appaloosa stallions are influential overall, by discipline (English, Western, Cattle, and Racing) and by association (Trainer, Breeder, Promoter, and Exhibitor). An email survey was sent to the available emails of the ApHC membership. The survey responses were analyzed resulting in three stallions being designated overall influential. Those stallions were Dreamfinder, Prince Plaudit, and Goer. Interviews were conducted with ApHC members that had first-hand experience with the stallions to collect oral histories. The interviews were compared to archived information, statistics, and the survey data to give a complete oral history of each stallion. The theory of social construction is a concept that contributes to the creation of a group. Social construction works through the use of oral histories, which acts to record perspectives of the past. Oral histories are important for letting individuals know the past and where they come from. This document shows the influence of specific Appaloosa stallions on the industry since 1960. It informs members of the ApHC why these stallions are considered influential. The oral histories intensify the written facts already documented on these stallions. Oral histories add validity to what is already considered fact. This allows future Appaloosa enthusiasts to understand the history of their beloved breed.

The obligation to maintain and develop professional competence throughout an individual’s career is a fundamental requirement of a maintaining a professional accounting designation. Accountants can select their continuing professional development (CPD) from a number of modalities. The study was a cross sectional sample created by self selection from a researchers' email invitation to accountants in Canada to determine which modalities accountants preferred, and the selection factors they used in making those selections. A total of 428 accountants from across Canada completed the online survey. The results found that the accountants had taken courses in all modalities presented with live seminar and live webinar being the most popular modalities. Accountants preferred synchronous over asynchronous courses. The factors most important to accountants are content, cost and CPD hour requirements. Generally, the differences found in selection factors for distance versus face-to-face modalities related to the flexibility of the distance course to reduce time away from work. The ranking of selection factors for synchronous courses in general did not differ from those for asynchronous courses with the exception of self-paced courses where the pace and time away from work were ranked higher than for other courses. Further research is suggested to determine the value of both live and recorded seminars and webinars, as well as potential opportunities for mobile modality use for CPD courses. Additional research should be conducted to determine why differences were found in ranking in demographics in order to ensure that future CPD courses are offered in modalities that provide benefits for all respondents. / 2012-06

k-core is a notion capturing the cohesiveness of a subgraph in a social network graph. Most of the current research work only consider pure network graphs and neglect an important property of the nodes: influence. Li, Qin, Yu, and Mao introduced a novel community model called k-influential community which is based on the concept of k-core enhanced with node influence values. In this model, we are interested not only in subgraphs that are well-connected but also have a high lower-bound on their influence. More precisely, we are interested in finding top r (with respect to influence), k-core communities. We present novel approaches that provide an impressive scalability in solving the problem for graphs of billions of edges using only a consumer-grade machine. / Graduate

The main purpose of this study was to explore how second-generation young adults with foreign background understand their ethnic identities and how they relate to their national identities. Semi-structured interviews with 7 second-generation young adults with foreign background were conducted. The basis for our analysis was social identity theory, identity theory and previous research. As the result shows, the participants in this study had developed an understanding of their ethnic identities in relation to their national identities based on influential factors. The influential factors that elicited these understandings of their ethnic identities in relation to their national identities were: influential people and cultural influences. On the basis of these influential factors, it had become easier for some participants to identify themselves more with their ethnic identities. However, for other participants, the understanding of their ethnic identities did not influence their feelings of belongingness to the host society, which means they have considered themselves to belong to both their ethnic and national identities. For those participants who could not identify themselves with both their ethnic identities and relate to their national identities chose to identify themselves with something else, which in this case religion.

Graphs are commonly selected as a model of scientific information: graphs can successfully represent imprecise, uncertain, noisy data; and graph theory has a well-developed mathematical apparatus forming a solid and sound foundation for graph research. Design and experimental confirmation of new, scalable, and practical analytics for massive graphs have been actively researched for decades. Our work concentrates on developing new accurate and efficient algorithms that calculate the most influential nodes and communities in an arbitrary graph. Our algorithms for graph decomposition into families of most influential communities compute influential communities faster and using smaller memory footprint than existing algorithms for the problem. Our algorithms solving the problem of influence maximization in large graphs use much smaller memory than the existing state-of-the-art algorithms while providing solutions with equal accuracy. Our main contribution is designing data structures and algorithms that drastically cut the memory footprint and scale up the computation of influential communities and nodes to massive modern graphs. The algorithms and their implementations can efficiently handle networks of billions of edges using a single consumer-grade machine. These claims are supported by extensive experiments on large real-world graphs of different types. / Graduate

Influential person Abstract The theme of this thesis is a legal understanding of the term 'influential person' which entered the Czech legal system due to significant changes in private law, especially when the Act no. 90/2012 Coll., on Business Corporations and Cooperatives and the Act no. 89/2012 Coll., Civil code came into effect. The thesis is primarily focused on identifying and analyzing the particularities of the term, its contribution to the law of business corporations and also its use in legal practice. The thesis relies on the methodology of analyzing the valid legal enactment of influence in comparison to its evolution, legal practice and scholarly literature. The thesis is divided into five chapters in total. The first chapter introduces the term corporate group as a sign of economic concentration, and subsequently the specifics and forms of corporate groups are being discussed. The next part briefly describes the evolution and basic scheme of legal enactment of corporate groups in the Czech Republic, especially the changes in the Act no. 513/1991 Coll., Commercial code and the local sources involved in the enactment. Furthermore it also explores the legal enactment of corporate groups according to the European Union. The third chapter deals with the valid legal enactment of influence according...

In surveys, one may face the problem of influential units at the estimation stage. A unit is said to be influential if its inclusion or exclusion from the sample has a drastic impact on the estimates. This is a common situation in business surveys as the distribution of economic variables tends to be highly skewed. We study and examine some commonly used estimators and predictors of a population total and propose a robust estimator and predictor based on an adaptive tuning constant. The proposed tuning constant is based on the concept of conditional bias of a unit, which is a measure of influence. We present the results of a simulation study that compares the performance of several estimators and predictors in terms of bias and efficiency.

Diese Studie konzentriert sich auf eine vergleichende Erforschung über lebenslange Lernmotivation und deren Einflussfaktoren in China und Deutschland. Da das lebenslange Lernen ein weithin anerkanntes System ist, welches internationale Bedeutung, reichliche Konnotation, Multiplex-Programmen und komplexe Verzweigungen enthält, scheinen die Erforschung und Analyse über das lebenslange Lernen und konkretes Lernverhalten, Strategien, Theorien, Performanz und Einflussfaktoren immer extrem schwierig zu sein. Zum Analysieren der konkreten Lernerfahrungen sowie Einstellungen und Gedanken von normalen Personen über das lebenslange Lernen werden biographische Erzählung Interview als Instrument der Datenerhebung und die Erforschung Schritte vom Grounded Theory als Forschungsmethode verwendet. Insofern ist eine empirische Theorie auf unseren Forschungsgegenstand zu entwickeln. Die interviewten Personen für dieser Studie besteht aus 20 ausgewählten chinesischen und 20 ausgewählten Deutschen mit unterschiedlichem Hintergrund und Konventionen. Untersucht werden die ganzen Lernerfahrungen und Ansichten von ihnen über die Motivationen und Einflussfaktoren auf ihr eigenes lebenslanges Lernen. Basiert auf einen Analyseprozess von offenen, axialen und selektiven Codierung kann man feststellen, dass die Lernmotivationen und Einflussfaktoren auf lebenslanges Lernen vor allem aus vier Hauptgruppen, nämlich Familie, Gesellschaft, Individuum, sowie Schulen bzw. Mitschüler und Lehrer kommen. Zum Beschreiben der Zusammenhänge zwischen diesen Faktoren und den typischen Kategorien von Einflussfaktoren in den einzelnen Ländern zu beschreiben, werden sie in „Postmoderne“, „Scandinavian“, „Transformation“ und „Traditionelle Asiatische“ Typen mit dem „Ideal-Typ“ als Leitgedanke eingeteilt . In der konkreten Analyse der Arten der Motivation und Einflussfaktoren auf lebenslanges Lernen von Deutschen und Chinesen, werden die „Autonome“ und „Autoritären“ Features auf der y-Koordinate, und die „Individuell“ und „Sozial“ Faktoren auf die x-Koordinate beschriftet, damit die Cluster-Formen der Faktoren in den einzelnen Ländern auf die Diagramme zeichnet werden können. Die konkrete Analyse der Einflussfaktoren und Motivationen beruht auf dem allgemeinen Hintergrund der nationalen Bedingungen und der Realität der Bildungsentwicklung in jedem Land. Jede Hauptkategorie der Einflussfaktoren und Motivationen hat seinen tiefen Grund von der konkreten Makro-, Meso- und Mikrorealität, wie die nationalen Geschichte, Gesetzessystem, Bildungseinrichtungen, Lehr- und Lernpraktiken, wirtschaftliche Situationen, Gesamt Figuration und Bildungskulturen, sowie das Bildungssystem. Durch Analysieren und Vergleichen kann festgestellt werden, dass jedes Land oder Region ihre eigenen Eigenschaften, Implementierungsmethode oder Merkmale des lebenslangen Lernens sowie ihrer Bildungspolitik, Bildungserfahrungen, Lernmethoden, Prinzipien, Lern- und Lehrerfahrungen hat. Zur Verbesserung der Bildungsreformation und deren Fortschritt könnte man erfolgreiche Erfahrungen und Geschichte als Referenz verwenden, damit eigenes erfolgversprechendes Bildungssystem bzw. erfolgversprechende Bildungspolitik gründet werden könnte. Auf der Grundlage von Schlussfolgerungen und Ergebnisse dieser Erforschung sind Vorschläge und Anleitung für die Förderungen des lebenslangen Lernens zu erschließen, die sich in der Zukunft nicht nur in China und Deutschland, aber auch in anderen Industrie- und Entwicklungsländern für verbesserte Leistungen in diesem Bereich anbieten.