Empirical likelihood, which was pioneered by Thomas and Grunkemeier (1975) and Owen (1988), is a powerful nonparametric method of statistical inference that has been widely used in the statistical literature. In this thesis, we investigate the merits of empirical likelihood for various problems arising in ratio estimation. First, motivated by the smooth empirical likelihood (SEL) approach proposed by Zhou & Jing (2003), we develop empirical likelihood estimators for diagnostic test likelihood ratios (DLRs), and derive the asymptotic distributions for suitable likelihood ratio statistics under certain regularity conditions. To skirt the bandwidth selection problem that arises in smooth estimation, we propose an empirical likelihood estimator for the same DLRs that is based on non-smooth estimating equations (NEL). Via simulation studies, we compare the statistical properties of these empirical likelihood estimators (SEL, NEL) to certain natural competitors, and identify situations in which SEL and NEL provide superior estimation capabilities. Next, we focus on deriving an empirical likelihood estimator of a baseline cumulative hazard ratio with respect to covariate adjustments under two nonproportional hazard model assumptions. Under typical regularity conditions, we show that suitable empirical likelihood ratio statistics each converge in distribution to a 2 random variable. Through simulation studies, we investigate the advantages of this empirical likelihood approach compared to use of the usual normal approximation. Two examples from previously published clinical studies illustrate the use of the empirical likelihood methods we have described. Empirical likelihood has obvious appeal in deriving point and interval estimators for time-to-event data. However, when we use this method and its asymptotic critical value to construct simultaneous confidence bands for survival or cumulative hazard functions, it typically necessitates very large sample sizes to achieve reliable coverage accuracy. We propose using a bootstrap method to recalibrate the critical value of the sampling distribution of the sample log-likelihood ratios. Via simulation studies, we compare our EL-based bootstrap estimator for the survival function with EL-HW and EL-EP bands proposed by Hollander et al. (1997) and apply this method to obtain a simultaneous confidence band for the cumulative hazard ratios in the two clinical studies that we mentioned above. While copulas have been a popular statistical tool for modeling dependent data in recent years, selecting a parametric copula is a nontrivial task that may lead to model misspecification because different copula families involve different correlation structures. This observation motivates us to use empirical likelihood to estimate a copula nonparametrically. With this EL-based estimator of a copula, we derive a goodness-of-fit test for assessing a specific parametric copula model. By means of simulations, we demonstrate the merits of our EL-based testing procedure. We demonstrate this method using the data from Wieand et al. (1989). In the final chapter of the thesis, we provide a brief introduction to several areas for future research involving the empirical likelihood approach.

Japan obtained equal status with the west imperialism, like Britain and North America, after defeating Russia in 1905. For promoting their mainland policy, they set up the semi-official and semi-private company- South Manchuria Railway (SMR). It owned a huge Research Bureau to investigate some aspects like railway, natural resources, transportation and military, not only for satisfying colonial goal but also for producing rich, valuable and multidimensional knowledge .During forty-years, the Research Bureau attracted and enrolled many Japanese who had interests on, or preference to China. Japanese took this process as a approach or domain to contact with China. This process also reflected their own ideology, image and relative location to China by the rise of the Empire of Japan. This dissertation starts from reviewing important research results, such as Shina Resistance Report, Nōson Chūgoku Kankō Chōsa Surveys. The discussion goes further to four researchers in the SMR: Shūmei Ōkawa, Tachibana Shiraki, Amano Waranosuke and Itō Takeo, who were with various academic background and even standpoint. The investigators attempted to construct their own research approach and meanwhile suffered from dealing it with the subjective power structure. The last section focuses on the academic debate after the war time, in term of controversial interpretation about Mantetsu knowledge from Japanese Sinology. From these three perspectives, the dissertation intends to take Mantetsu as a example to portray the context, power relationship and conflicts within research institute in Japan. It would therefore generalize objectivity, autonomy and path-dependence from the Mantetsu knowledge.

This study mainly discusses the effect, in country level, of minority shareholder protection on shareholder wealth during mergers and acquisitions (M&A). In particular, based on the index of anti-director rights (ADRI) developed by LLSV (1998) and the index of shareholder protection index (SPI) by John Armour et al.(2009), I empirically examine the linkage between M&A activities and indexes as well as the components of these indexes. This study expects the result may show some relevance between of indices and M&A activities, and the legal value of this relevance. The purpose is to show whether minority shareholder protection is workable in M&A activities, and whether it can facilitate M&A markets. To begin with, this paper discusses LLSV¡¦s uniqueness in corporate law study ¡V using empirical method to value whether corporate law matters or not around the world. Then, I analyze LLSV¡¦s possible defects, review criticisms and effects they had incurred. Secondly, we design a study to compare the revised LLSV methodology developed by the Harvard scholar Spamann with SPI index through stock market and M&A market. I also code China¡¦s and Taiwan¡¦s data to make up the lack of samples of cross level variation, and take this as the basis for corporate institutional comparison. This study reports that each of sub-indexes from ADRI and SPI has different relevance to M&A activities: three are positive, five are negative, three are insignificant, and two are valueless of discussion (definition or design defect). Thus we may see the importance of law quantification. We appreciate further research and authorities¡¦ consideration following our work in Taiwan. Finally, the contribution of this study is to attempt to integrate empirical and comparative legal analysis, in response to global corporate governance issues of promoting cross research. On policy implications is that it can predict some investor protection mattes, direct the way of policy adjustment. Besides, this study can also suggest specific amendment for Company Law and Securities law to re-examine how to balance between market development and the protection of minority shareholders.

A major part of the terrestrial sediment in the ocean comes from the land via river plume. There are four stages in sediment dispersal from rivers into the sea: supply via plume, initial deposition, resuspension and transport by waves and currents or by the slope failure, and long-term net accumulation. We can understand the dispersion and transport of the river plume by in situ observations of hydrodynamic of the plume field. Therefore, it is helpful to study river plume hydrodynamics, such as winds, tides, waves, and currents. The purpose of this study is to identify the type of plume dynamics by analyzing the temporal and spatial variability of hydrological structures observed around the Gaoping River mouth. We observed the bottom and surface time series of temperature, salinity, turbidity, suspended sediment concentration, and velocity profile by instrument mounted at the tetrapods and a moored buoy during July 28 to 30 in 2009 and July 30 to August 2 in 2011. Besides, we investigated the spatial structures of the river plume in Gaoping River mouth by using a fishing boat in 2009. We also acquired satellite images to assist our study. The results showed that the river discharges during 2009 was lower than daily average discharge. Combined the temporal and spatial observations and satellite images, we determined that the river plume turned west during the ebb tide was influenced by Coriolis force and winds. The buoyancy-driven current velocity was 0.15 m/s and the maximum of wind-driven current velocity was 0.30 m/s. The wind strength index (Ws) determines whether a plume¡¦s along-shelf flow is in a wind-driven or buoyancy-driven state. Ws is the ratio of the wind-driven and buoyancy-driven along-shelf velocities. If |W_s | > 1 on average the wind velocity more than 5.9 m/s. The wind velocity reached this threshold during most of the ebb periods, and around that value in the flood time. Flood currents combined with cross-shore wind pushed the river plume to swing to the east. The data were analyzed by empirical orthogonal function (EOF) analysis. The results indicated that winds and waves were the main factors influencing plume dynamics during low-discharge period. During the field experiment in 2011, the river discharge was greater than daily average discharge. The buoyancy-driven and the maximum of wind-driven current velocities were 0.30 and 0.12 m/s, respectively. The wind velocity did not reach the threshold that was 11.67 m/s. The buoyancy-driven current was more significant than wind-driven current. By analyzing the ocean color of satellite images, the river plume was spreading from the river mouth and toward west during ebb. The time series data also showed that there was plume signal at the same time. The average cross-shore current velocity was 0.52 m/s, being larger than the buoyancy-driven current. Therefore, the tide was the main factor deciding where the plume discharged. The first eigemode of EOF suggested that current was the most important factor influencing plume dynamics during high-discharge period. The second eignmode described the dominant influence of wind.

In this study, the semi-empirical approach is introduced to accurately estimate the probability distribution of complex non-linear random variables in the field of wavestructure interaction. The structural form of the semi-empirical distribution is developed based on a mathematical representation of the process and the model parameters are estimated directly from utilization of the sample data. Here, three probability distributions are developed based on the quadratic transformation of the linear random variable. Assuming that the linear process follows a standard Gaussian distribution, the three-parameter Gaussian-Stokes model is derived for the second-order variables. Similarly, the three-parameter Rayleigh-Stokes model and the four-parameter Weibull- Stokes model are derived for the crests, troughs, and heights of non-linear process assuming that the linear variable has a Rayleigh distribution or a Weibull distribution. The model parameters are empirically estimated with the application of the conventional method of moments and the newer method of L-moments. Furthermore, the application of semi-empirical models in extreme analysis and estimation of extreme statistics is discussed. As a main part of this research study, the sensitivity of the model statistics to the variability of the model parameters as well as the variability in the samples is evaluated. In addition, the sample size effects on the performance of parameter estimation methods are studied. Utilizing illustrative examples, the application of semi-empirical probability distributions in the estimation of probability distribution of non-linear random variables is studied. The examples focused on the probability distribution of: wave elevations and wave crests of ocean waves and waves in the area close to an offshore structure, wave run-up over the vertical columns of an offshore structure, and ocean wave power resources. In each example, the performance of the semi-empirical model is compared with appropriate theoretical and empirical distribution models. It is observed that the semi-empirical models are successful in capturing the probability distribution of complex non-linear variables. The semi-empirical models are more flexible than the theoretical models in capturing the probability distribution of data and the models are generally more robust than the commonly used empirical models.

This thesis was concerned on the investigation of mechanical properties of centrally notched and unnotched AS-4/PEEK (APC-2) composite laminates due to static tensile and tension-tension (T-T) fatigue tests empirically and systematically. Then, statistical analyses were used to determine and quantify the significant thermomechanical variables that influence the durability/life of the composite laminates. Typical laminates were made from sixteen prepregs of APC-2 and manufactured by a modified curing process. After drilling one hole with various diameters in the center of the samples respectively, the lay-ups were conducted on tension fracture and T-T fatigue test at different temperatures. From the parametric study we achieved the important results as follows. The cross-ply laminate possesses the higher ultimate strength, fatigue strength and longitudinal stiffness than those of the quasi-isotropic at the same temperature. Notch effect decays the laminate strength seriously, but changes the stiffness irregularly. As test temperature rising both strength and stiffness of lay-ups degrade significantly. Combining both effects of notch and temperature under severe environmental condition, it is found the cross-ply laminate possesses more resistance than that of the quasi-isotropic to cyclic loading. However, the quasi-isotropic laminate is more capable of sustaining the original strength than that of the cross-ply. Finally, the multiple regression analysis results showed that the hygrothermal environmental effects and cyclic loading were decoupled for APC-2 composite system. A semi-empirical model, reliably set up after the said programs, predicts conservative values, and should be adequate for use in preliminary designs. That is the main contribution in this study. Also, for the purposes of design and application, the predicted models efficiently treat experimental data instead of conventional curve-fitting methods.

Analysis of large networks in biology, science, technology and social systems have become very popular recently. These networks are mathematically represented as graphs. The task is then to extract relevant qualitative information about the empirical networks from the analysis of these graphs. It was found that a graph can be conveniently represented by the spectrum of a suitable difference operator, the normalized graph Laplacian, which underlies diffusions and random walks on graphs. When applied to large networks, this requires computation of the spectrum of large matrices. The normalized Laplacian matrices representing large networks are usually sparse and unstructured. The thesis consists in a systematic evaluation of the available eigenvalue solvers for nonsymmetric large normalized Laplacian matrices describing directed graphs of empirical networks. The methods include several Krylov subspace algorithms like implicitly restarted Arnoldi method, Krylov-Schur method and Jacobi-Davidson methods which are freely available as standard packages written in MATLAB or SLEPc, in the library written C++. The normalized graph Laplacian as employed here is normalized such that its spectrum is confined to the range [0, 2]. The eigenvalue distribution plays an important role in network analysis. The numerical task is then to determine the whole spectrum with appropriate eigenvalue solvers. A comparison of the existing eigenvalue solvers is done with Paley digraphs with known eigenvalues and for citation networks in sizes 400, 1100 and 4500 by computing the residuals.

As export competition becomes more intense and export success vital for survival (Katsikeas, 1994), so the effective processing and use of information regarding the international environment becomes a critical prerequisite for gaining competitive advantage (Leonidou and Theodosiou, 2004). Symbolic use of information is one type of information use, which although relatively underexplored to date, may be the most prevalent form of information use within organisations – especially in an export setting (Beyer and Trice, 1982). Symbolic use occurs when information is used for purposes other than the ones which led to its collection (Menon and Varadarajan, 1992). Symbolic use of information has been conceptualised as a multi-dimensional construct encompassing various dimensions (Vyas and Souchon, 2003). Examples include “exporters that engage in distorting market research findings, taking conclusions out of context, disclosing only the findings that confirm an executive‟s predetermined position or consciously ignoring information” (Toften and Olsen, 2004, p. 106). Symbolic use can also legitimate decisions reached on the basis of intuition or managerial assumptions (Vyas and Souchon, 2003). Although conceptual propositions of the potential relationship between each of the symbolic use dimensions and performance exist (Vyas and Souchon 2003), no empirical research has yet been undertaken. As a result, little is known about how and why symbolic use of export information may affect export performance, and under what circumstances. Furthermore, reliable and valid measures for each one of the symbolic use dimensions are absent in the literature. The purpose of this thesis is to fill in these research gaps. In so doing, a combination of both qualitative and quantitative methods is employed. The exploratory phase takes the form of in depth interviews with export decision makers in the UK. The data collected in this exploratory phase are analysed through the use of within-case and cross-case displays as per Miles and Huberman (1994) and are used not just for hypothesis development, but also to identify potential outcomes of using information symbolically in specific ways and to create pools of items for the development of measures of symbolic use. (Continues...).

KM is the process of creating value from the intangible assets of an enterprise. It deals with how best to leverage knowledge internally in the enterprise (in its individual employees, and the knowledge that gets built into its structures and systems) and externally to the customers and stakeholders. As KM initiatives, projects and systems are just beginning to appear in organisations, there is little research and empirical field data to guide the successful development and implementation of such systems or to guide the expectations of the potential benefits of such systems. In addition, about 84 per cent of KM programmes failed or exerted no significant impact on the adopting organisations worldwide due to inability to consider many critical factors that contribute to the success of KM project implementation. Hence, this study is an exploratory investigation into the KM implementation based on an integrated approach. This includes: (1) a comprehensive review of the relevant literature; (2) a comprehensive analysis of secondary case studies of KM implementations in 90 organisations presented in the literature, in order to arrive at the most critical factors of KM implementation and their degree of criticality; (3) exploratory global survey of 92 organisations in 23 countries that have already implemented or are in the process of implementing KM; (4) in-depth case studies of four leading organisations to understand how KM implementation processes and the critical factors identified are being addressed. Based on the empirical findings of the study, 28 critical factors were identified that must be carefully considered in the KM implementation to achieve a successful project. Moreover, the study proposes an integrated model for effective KM implementation which contains essential elements that contribute to project success.

This paper presents the work in progress regarding an international research project based on an empirical survey. It focuses on the early stages of making the adoption decision, thereafter evaluating and selecting an Enterprise Resource Planning (ERP) system prior to implementation in Small to Medium sized Enterprises (SMEs). The project seeks to close some of the identified gaps in ERP research. In addition, it attempts to link the results of the early stages of decision making to implementation, usage and evolution success in order to allow important conclusions to be made, for example, on the best practices in decision making or decision quality and success. This project will be restricted to the case of ERP software but will also give insights into the potential of integrating ERP and other important applications such as Customer Relationship Management (CRM) or Supply Chain Management (SCM). The proposed research seeks to identify any differences and similarities contributing to the analysed research areas between British and Austrian companies. The choice of companies originating from two different regions in Europe is an important precondition in order to formulate results that will be applicable to the European Union in general. Due to the pervasive nature of ERP systems, our research results should be of interest to a wide range of professional and scholarly communities (from software engineering to accounting), in addition to the Information Systems (IS) field. The results presented should especially help practitioners in SMEs facing the important task of introducing an ERP system into their company. (author's abstract) / Series: Working Papers on Information Systems, Information Business and Operations