<p>Syftet med uppsatsen är att försöka förklara vad det är som påverkar tiden som en mamma ammar. För att undersöka vad det är som påverkar tiden som en mamma ammar, har en Zero inflated negative binomial-modell (ZINB-modell) tagits fram. Resultaten visar att det som avgör hur länge en mamma kommer att amma är: Graviditetens längd, mammans ålder, mammans rökvanor under graviditetens sista månader, mammans rökvanor samt mammans nationella ursprung.</p>

Thesis (Ph. D.)--Ohio State University, 2006. / Title from first page of PDF file. Includes bibliographical references (p. 135-139).

Syftet med uppsatsen är att försöka förklara vad det är som påverkar tiden som en mamma ammar. För att undersöka vad det är som påverkar tiden som en mamma ammar, har en Zero inflated negative binomial-modell (ZINB-modell) tagits fram. Resultaten visar att det som avgör hur länge en mamma kommer att amma är: Graviditetens längd, mammans ålder, mammans rökvanor under graviditetens sista månader, mammans rökvanor samt mammans nationella ursprung.

A pesar de que los investigadores en el ámbito de la gestión empresarial le han prestado atención creciente desde tan solo hace unas décadas, el Gobierno Corporativo (GC) no es un concepto nuevo. Así, la reciente crisis financiera mundial ha generado entre los accionistas un creciente y revitalizado interés por el tema, al ver éstos una reducción importante en el valor de sus acciones. Como reacción lógica, se acusa al grupo directivo, y a los miembros de los órganos de gobierno corporativo, de no preservar adecuadamente los intereses generales. Este estudio analiza el impacto de algunas variables relativas al GC en los resultados de las empresas, para ello se recogen las variables utilizadas en estudios previos, a la vez que se proponen nuevas variables, pues los resultados obtenidos hasta el momento ofrecen resultados contradictorios tanto en las aplicaciones circunscritas a países concretos como en los estudios de ámbito internacional.Los datos utilizados en la parte empírica del trabajo provienen de diecisiete países miembros de la OCDE, de los cuales dieciséis son miembros de la Unión Europea, mientras que el restante corresponde a los EEUU. Adicionalmente al estudio del GC, también se presenta una investigación relativa a los niveles de eficiencia técnica y productividad entre diferentes países y sectores industriales, realizando estimaciones bootstrap. El trabajo realiza una revisión de los códigos de GC, y de los índices propuestos, para, a continuación, escoger aquellos que resultan más adecuados en la elaboración de un índice general de CG. Los indicadores escogidos son: la separación del Director Gerente y la estrategia financiera de las empresas. Los tradicionales indicadores de resultados utilizados en investigaciones previas también son revisados, al igual que los indicadores de protección de los inversores.Después de estimar los niveles de eficiencia técnica y de productividad, estos resultados son utilizados en una segunda etapa, que utiliza técnicas de estimación paramétrica, en el que, junto a otras variables de resultado, se ponen en relación con variables de GC. Con el fin de conseguir estimaciones robustas, se realizan ajustes para corregir los problemas causados por la endogeneidad de las variables independientes, la heteroscedasticidad y la correlación serial. También son investigadas estimaciones cuadráticas y lineales a trozos. En general, se encuentra soporte para la mayoría de las hipótesis que relacionan el GC con los resultados, excepto en el caso de la relativa a la protección del inversor. Así, los índices de concentración de la propiedad implican una reducción en la valoración del mercado junto a un incremento en los niveles de eficiencia técnica y unos resultados variables en los niveles de resultados. El tamaño del Consejo de Administración tiene un efecto negativo en la mayoría de los indicadores aunque, sin embargo, exhibe una relación cóncava con la valoración del mercado. La presencia de miembros externos ejerce un impacto positivo en la valoración del mercado, un impacto negativo en los niveles de eficiencia técnica y una influencia insignificante en los otros indicadores de resultado. Por su parte, se observa una relación negativa entre el número de sucesivos códigos de conducta y los indicadores de resultados. Teniendo en cuenta los anteriores resultados, se propone una medida global de los resultados. Asimismo, se recomienda expandir el marco teórico usado para examinar la relación entre los resultados y las características del GC. En este sentido, la perspectiva de la moderna teoría de los grupos de interés resultaría recomendable, pues la teoría de la agencia resulta insuficiente para explicar las características de los órganos de GC y cómo es que las decisiones de inversión de ciertos accionistas no están guiadas por los postulados de la teoría financiera. / Corporate governance is not a new concept although business researchers have only shown exponential interest dating back a few decades. The recent financial turmoil of global proportions has merited a revitalised interest as shareholders have seen their shareholding wealth tumble markedly. Management and the board of directors of companies have been accused of not doing much in safeguarding the interests of their shareholders. This study revisits the impact of some corporate governance variables on performance by extending the performance measures of previous studies; as extant empirical literature purveys contradicting results in both single and cross-country studies.Data from seventeen OECD countries; sixteen of which are in the European Union and the other being the USA is utilised. These countries have similar or different legal origins and different levels of investor protection. In addition to the study of governance, an investigation is made of technical efficiency and productivity differences between the countries and the industrial sectors represented. This is achieved by using a bootstrap approach that enables better statistical inferences through data envelopment analysis techniques. This is to see if differences in corporate governance practices are related to differences in technical efficiency and productivity growth. This study involves an extensive literature review of corporate governance codes and indices, narrowing down to a few of these governance characteristics used in preparing the governance index. These are: corporate shareholding concentration and type; board characteristics of size and composition; CEO-chairman separation, and; a firm's financial policy. The literature goes on to link these characteristics to performance, reviewing the performance measures traditionally used to evaluate the effects of corporate governance. A review of studies in investor protection is also given. The various control variables used in moderating the link between performance and governance are discussed. The concepts of technical efficiency and total factor productivity are explained into detail here and some results of previous studies that have sought to link these with corporate governance are reviewed. The governance characteristics are linked to investor protection and performance through the conceptual framework of positive agency theory and institutional theory. In the empirical aspect, technical efficiency and productivity analyses are carried out. After the conventional univariate and bivariate analyses of the data, cross-sectional analyses are performed. Justification is then provided for performing pooled analysis, curtailing endogeneity problems. Pooling data gives rise to issues of panel heteroskedasticity and serial correlation. A Prais-Winsten cross-sectional time series transformation is utilised to eschew these problems. In the case of technical efficiency and total factor productivity, this method is inappropriate as the data is censored, so a bootstrapped truncated regression is utilised. In a section of the literature, the relationship between governance and valuation has been argued to be non-monotonic/non-linear. This study utilises piecewise linear and quadratic specifications to investigate this argument. Subsequently, the global model developed for this study is tested at the individual country levels. Finally, the link between corporate governance, investor protection and valuation is investigated. In general, there is support for most of the hypotheses of governance effects on performance except the influence of investor protection. Concentrating ownership leads to decreased market valuation but increased technical efficiency and mixed effects on profitability. Board size has a negative effect on most of the performance proxies but it exhibits a concave relationship with valuation. Separating the duties of the CEO and board chairman is of no import to firm performance. Board outsiders exert a positive impact on market valuation, a negative impact on technical efficiency and insignificant influences on the other performance measures. The number of governance codes introduced by a country has adjustment implications for firms as a negative influence on firm performance is observed.In the light of these findings, a composite measure of performance is recommended while the theoretical framework that is used to examine governance and performance issues needs to be expanded to accommodate contrasting conceptual frameworks. The stakeholder approach is particularly encouraged as positive agency theory on its own will not fully explain why firms are governed the way they are and why the investment decisions of some shareholding categories are not wholly from a financial view point.

Ce mémoire traite d'une application pratique de deux méthodes statistiques non paramétriques : le bootstrap et le test de permutation. La méthode du bootstrap a été proposée par Bradley Efron (1979) comme une alternative aux modèles mathématiques traditionnels dans des problèmes d'inférence complexe; celle-ci fournit plusieurs avantages sur les méthodes d'inférence traditionnelles. L'idée du test de permutation est apparue au début du XXème siècle dans les travaux de Neyman, Fisher et Pitman. Le test de permutation, très intensif quant au temps de calcul, est utilisé pour construire une distribution empirique de la statistique de test sous une hypothèse afin de la comparer avec la distribution de la même statistique sous l'hypothèse alternative. Notre objectif est de déterminer l'intervalle de confiance pour un estimateur à maximum de vraisemblance d'une méthode de cartographie génétique existante (MapArg, Larribe et al. 2002) et de tester la qualité de cet estimateur, c'est-à-dire d'établir des seuils de signification pour la fonction de la vraisemblance. Les deux méthodes utilisent le calcul répétitif d'une même statistique de test sur des échantillons obtenus à partir de l'échantillon initial, soit avec le «bootstrap», soit avec des permutations. Dans un test d'hypothèse, les deux méthodes sont complémentaires. Le but de ce mémoire est de proposer différentes variantes pour la construction de l'intervalle de confiance, et de tester des hypothèses distinctes, afin de trouver la meilleure solution adaptée pour la méthode MapArg. Pour faciliter la compréhension des décisions prises, un rappel de l'inférence statistique et des tests d' hypothèse est fait dans les chapitres 4 et 5 où la théorie du bootstrap et celle de test de permutation sont présentées. Comme les qualités d'un estimateur dépendent de la méthode utilisée pour le calculer, les chapitres 1 et 2 présentent la base biologique et la base en mathématiques sur lesquelles la méthode MapArg est construite, tandis qu'on trouvera dans le chapitre 3 une explication de la méthode MapArg. ______________________________________________________________________________ MOTS-CLÉS DE L’AUTEUR : Mutation, Recombinaison, Coalescence, Cartographie génétique, «Bootstrap», Test de permutation.

In this dissertation, we propose a set of computationally efficient methods based on approximating/representing nonlinear processes by linear ones, so-called linearization. Firstly, a linearization method is introduced for estimating the multiple frequencies in sinusoidal processes. It utilizes a regularized autoregressive (AR) approximation, which can be regarded as a "large p - small n" approach in a time series context. An appealing property of regularized AR is that it avoids a model selection step and allows for an efficient updating of the frequency estimates whenever new observations are obtained. The theoretical analysis shows that the regularized AR frequency estimates are consistent and asymptotically normally distributed. Secondly, a sieve bootstrap scheme is proposed using the linear representation of generalized autoregressive conditional heteroscedastic (GARCH) models to construct prediction intervals (PIs) for the returns and volatilities. Our method is simple, fast and distribution-free, while providing sharp and well-calibrated PIs. A similar linear bootstrap scheme can also be used for diagnostic testing. Thirdly, we introduce a robust lagrange multiplier (LM) test, which utilizes either the bootstrap or permutation procedure to obtain critical values, for detecting GARCH effects. We justify that both bootstrap and permutation LM tests are consistent. Intensive numerical studies indicate that the proposed resampling algorithms significantly improve the size and power of the LM test in both skewed and heavy-tailed processes. Moreover, fourthly, we introduce a nonparametric trend test in the presence of GARCH effects (NT-GARCH) based on heteroscedastic ANOVA. Our empirical evidence show that NT-GARCH can effectively detect non-monotonic trends under GARCH, especially in the presence of irregular seasonal components. We suggest to apply the bootstrap procedure for both selecting the window length and finding critical values. The newly proposed methods are illustrated by applications to astronomical data, to foreign currency exchange rates as well as to water and air pollution data. Finally, the dissertation is concluded by an outlook on further extensions of linearization methods, e.g., in model order selection and change point detection.

Both developing and developed countries have witnessed the very heart position of small business in the contribution of economic growth and job creation. Nevertheless, the appetite for funds of new enterprises is still not satisfied nowadays, which limits the further blossom of entrepreneurship. Concerning about this problem, our research tries to investigate and describe financing sources of companies in seed/early stage and understand the implications of entrepreneurial leadership in the process of fundraising. Besides, this study involves three business ecosystems: America, France and China in the international context.Following the grounded theory as the researching path, this thesis is considered as a combination of realistic research about financing sources and interpretative research about entrepreneurial leadership. The study is based upon secondary data, which are widely gathered from USA, France and China. In order to achieve in-depth perspectives, empirical explorations are conducted mainly through example studies and face-to-face dialogues with experts including an entrepreneur, a consultant in relation with investors, a bank manager and a project manager.A comprehensive understanding is realized as a result of this research:• American business ecosystem proves its leading position in fundraising support for bootstrap-step companies. As to French ecosystem, it is evolving and represents various particularities regarding regulations, structural mentalities and policies. The Chinese one is fairly different due to the affection of the Communism regime but also the particularly important role of network in doing business.• Entrepreneurial leadership is helpful in fundraising process. And enactment of leadership is quite different due to diverse culture and financing sources. Through the thesis, we interpret how entrepreneurial leadership could be helpful for fundraising in each business ecosystem.• Beyond academic sphere, this research reveals significant benefits and potentials for bridging fund flow among three business ecosystems. It shows a big entrepreneurial opportunity for people who have knowledge and network to break cultural boundaries and construct this “bridge”.In no wise this study aims at explaining or prescribing. By studying each ecosystem for entrepreneurial leaders, we hope to establish an understanding of this topic that could be further examined.

Wireless sensor networks (WSNs) have received huge attention during the recent years due to their applications in a large number of areas such as environmental monitoring, health and traffic monitoring, surveillance and tracking, and monitoring and control of factories and home appliances. Also, the rapid developments in the micro electro-mechanical systems (MEMS) technology and circuit design lead to a faster spread and adoption of WSNs. Wireless sensor networks consist of a number of nodes featured in general with energy-limited sensors capable of collecting, processing and transmitting information across short distances. Clock synchronization plays an important role in designing, implementing, and operating wireless sensor networks, and it is essential in ensuring a meaningful information processing order for the data collected by the nodes. Because the timing message exchanges between different nodes are affected by unknown possibly time-varying network delay distributions, the estimation of clock offset parameters represents a challenge. This dissertation presents several robust estimation approaches of the clock offset parameters necessary for time synchronization of WSNs via the two-way message exchange mechanism. In this dissertation the main emphasis will be put on building clock phase offset estimators robust with respect to the unknown network delay distributions. Under the assumption that the delay characteristics of the uplink and the downlink are asymmetric, the clock offset estimation method using the bootstrap bias correction approach is derived. Also, the clock offset estimator using the robust Mestimation technique is presented assuming that one underlying delay distribution is mixed with another delay distribution. Next, although computationally complex, several novel, efficient, and robust estimators of clock offset based on the particle filtering technique are proposed to cope with the Gaussian or non-Gaussian delay characteristics of the underlying networks. One is the Gaussian mixture Kalman particle filter (GMKPF) method. Another is the composite particle filter (CPF) approach viewed as a composition between the Gaussian sum particle filter and the KF. Additionally, the CPF using bootstrap sampling is also presented. Finally, the iterative Gaussian mixture Kalman particle filter (IGMKPF) scheme, combining the GMKPF with a procedure for noise density estimation via an iterative mechanism, is proposed.

How to evaluate mutual fund performance correctly and determine the investment targets of mutual funds are the important issues to investors. In this study, we apply an innovative bootstrap statistical technique, to solve the small sample size problem and the distribution assumption disturbance in previous research. We examine the performance of domestic open-end mutual funds over the period from 1998 to 2003 using five performance measurement models. We further test the persistence of mutual fund performance. This study shows that¡G 1. On average, mutual fund managers do not own superior ability in stock selection. Most funds experiencing abnormal performance may simply result from good luck, since random selection also creates abnormal performance. 2. Mutual fund managers do not own market-timing ability. Classified further by investment objectives, the sample indicates that only the group of small-scale stocks shows significant market-timing ability. 3. Performance persistence does not exist no matter in long-term or short-term period.

none