Herewith are presented the results of an investigation the statistical power of USP compendial release tests and recommended alternatives. <br>The U.S. drug supply chain, formerly protected by a closed distribution network, is now threatened by the legal and illegal importation of drug products. Whereas quality can never be inspected into final products, compendial release standards may represent the only valid assessment that products of dubious origin would receive. Reliable tests for content uniformity and dissolution are required to protect the safety of the supply chain. A study was designed to test the hypothesis that existing compendial tests for content uniformity and dissolution would protect the supply chain against substandard and counterfeit drugs if basic field tests failed. <br>Compendial tests for content uniformity and dissolution were evaluated for statistical power using simulation studies. The results revealed that the revised content uniformity test, based on tolerance analysis, was subject to an unacceptable level of consumers' risk. The Bergum method proved to be an excellent secondary standard for product assessment and is recommended as an alternative to the USP method. Simulations with the USP dissolution test revealed significant weaknesses and inconsistencies in the test structure. Theoretical models and power assessments confirmed that the coverage specification of the dissolution test was an unacceptably high 50% coverage with 50% confidence. <br>A Bayesian D-optimal design program was used to investigate alternative methods to improve the coverage capability of the USP dissolution test. The result of this program was the identification of two alternatives to the existing USP procedure. The first alternative is based on the addition of attribute coverage tests to stages 2 and 3 of the USP test, whereas the second alternative is based on the concept of tolerance analysis. <br>Validation studies confirmed that both alternatives significantly improved the statistical power of the USP dissolution test without increasing the sample size or modifying the current three-stage procedure. The attribute test is non-parametric and behaves similarly to the existing USP with improved coverage, whereas the continuous alternative is more sensitive and is consistent with the recent revisions to the content uniformity test. / Mylan School of Pharmacy and the Graduate School of Pharmaceutical Sciences / Pharmaceutics / PhD / Dissertation

Dimension reduction is a vital tool in many areas of applied statistics in which the dimensionality of the predictors can be large. In such cases, many statistical methods will fail or yield unsatisfactory results. However, many data sets of high dimensionality actually contain a much simpler, low-dimensional structure. Classical methods such as principal components analysis are able to detect linear structures very effectively, but fail in the presence of nonlinear structures. In the first part of this thesis, we investigate the asymptotic behavior of two nonlinear dimensionality reduction algorithms, LTSA and HLLE. In particular, we show that both algorithms, under suitable conditions, asymptotically recover the true generating coordinates up to an isometry. We also discuss the relative merits of the two algorithms, and the effects of the underlying probability distributions of the coordinates on their performance. Model selection is a fundamental problem in nearly all areas of applied statistics. In particular, a balance must be achieved between good in-sample performance and out-of-sample prediction. It is typically very easy to achieve good fit in the sample data, but empirically we often find that such models will generalize poorly. In the second part of the thesis, we propose a new procedure for the model selection problem which generalizes traditional methods. Our algorithm allows the combination of existing model selection criteria via a ranking procedure, leading to the creation of new criteria which are able to combine measures of in-sample fit and out-of-sample prediction performance into a single value. We then propose an algorithm which provably finds the optimal combination with a specified probability. We demonstrate through simulations that these new combined criteria can be substantially more powerful than any individual criterion.

In a peer-to-peer shared ride system, transportation clients with traffic demand negotiate with transportation hosts offering shared ride services for ad-hoc ridesharing in a continuously changing environment, using wireless geosensor networks. Due to the distinctive characteristic of this system—a complex and non-deterministic transportation network, and a local peer-to-peer communication strategy—clients will always have limited transportation knowledge, both from a spatial and a temporal perspective. Clients hear only from nearby hosts, and they do not know the future availability of current or new hosts. Clients can plan optimal trips prior to departure according to their current knowledge, but it is unlikely that these trips will be final optimal trip due to continuously changing traffic conditions. Therefore, it is necessary to evaluate the trip quality in this dynamic environment in order to assess different communication and wayfinding strategies. (For complete abstract open document)

This research aims to define and develop a methodology to assist an individual traveller to select healthier and more sustainable transport routes and modes among admissible transport options and highlight the trade-offs among multiple objectives in terms of health, economic, social and environmental benefits. It aims to assist an individual traveller with multi-objectives to make more informed decisions in route and mode planning. The objectives in the case study were identified as personal energy expenditure, travel time, travel cost, CO2 emissions and energy resource consumption concerning sustainability. / This research presents procedures for estimating a range of costs and benefits for journeys; procedures for determining the optimal route for an individual’s trip in an urban area based on cost and benefit estimates and preference weights for specific objectives; procedures for undertaking sensitivity analysis for the optimal route; and uses of the cost and benefit estimation and optimal route generation procedures to conduct a case study for a realistic journey in Melbourne. / An active transport journey planner model was developed in MS Excel to allow users to set constraints for most objectives and give their corresponding weightings, respectively. The recommended transport solution (the least total disutility one) and ranking of other options along with their detailed objective-related information are derived. A case study shows that the methodology developed could be applied in selecting more informed transport solutions based on the user’s multi-objective preferences. In addition, transport options incorporating more cycling and walking have the higher probability to deliver healthier and more sustainable solution to users if social, environmental concerns were considered beyond economic issues. Meanwhile, in sensitivity analysis, the tornado diagrams and spiderplots diagrams are used for demonstrating how sensitive each transport option’s disutility is to the weightings of objectives.

The main objective of this study is to develop requisite models for information and communication technology (ACT) adoption and diffusion in the banking industry in Thailand. The research, combining two study areas of multiple criteria decision-making (MCDM) and system dynamics (SD), is conducted using two research methodologies: system development and a case study of the Siam Commercial Bank PCL in Thailand.The study shows how to combine the two decision-making tools of MCDM and system dynamics effectively. The requisite group models of ICT adoption and diffusion provide ways to select the most preferred technology and to allow forward planning to diffuse the adopted technology more effectively. With an embedded decision support tool, decision-makers are able to apply the models with their available information, intuition, knowledge, and experience to improve their decision-making and enhance their learning.Initially, the research revealed that the Siam Commercial Bank currently employs various types of information and communication technologies (ICT) to facilitate work processes, fulfil customers' requirements, and retain its competitive advantage. However, the bank still confronts problems relating to technology adoption and diffusion.A requisite group model of ICT adoption was developed using MCDM as a decision making tool. The model illustrated how to select the most preferable technological alternative that fulfilled the mission of the bank. Results from the MCDM analysis revealed that the preferred technology was Extranet banking followed by a data warehouse. The requisite group model of ICT diffusion was further developed using the system dynamics approach in order to enhance understanding of system behaviour of the selected technology and then provide ways to diffuse it more effectively. The model analyses were divided into three sub-models of information ++ / and communication technologies (ICT), a data warehouse, and Extranet banking.The generic model of ICT can be applied to any particular technology. Results revealed that the pattern of technology diffusion follows the S curve and the dominant variables that may impact on technology diffusion are training, a backlog of problems, and market potential. Furthermore economic returns are obtained only after spending substantially on technological investment. Thus, it is necessary to balance between technological investment and economic returns. The model of diffusion of a data warehouse was developed highlighting the necessity of quality and quantity of knowledge workers. Therefore, training support is an important factor to diffuse this technology. On the other hand, the model of diffusion of Extranet banking revealed that the success of this technology comes from the acceptance by customers. Thus, perceived relative advantages, positive features of the technology and promotional advertising should be taken into consideration. The S curve pattern of technology diffusion is also confirmed by the two technologies.The policy for technology adoption involves the selection of technology, which best fits with identified criteria. The policy analyses of the three technologies confirm that the core important policies that increase technology diffusion and economic gains are increasing positive features of technology, decreasing perceived complexity, increased perceived relative advantages and increasing co-operation between IT people and users. If technology is to support the work performance in an organisation, training support is the dominant policy, whereas if technology facilitates customers directly, marketing strategy such as promotional advertising is vital.The study implied that the banking industry in Thailand is able to use ICT as levers for competitive advantage. ++ / However, technological investment in each bank differs depending on size, objectives and readiness in terms of capital and human resources.All the findings have implications for the bank and could be applied to other banks and general policy makers in various business enterprises.

Thesis (M.A.)--Naval Postgraduate School, 2008. / Description based on title page of source document ( viewed on April 28, 2008). Includes bibliographical references (p. 137-143).

Diss. (sammanfattning) Stockholm : Karol. inst., 2005. / Härtill 5 uppsatser.

Dissertation (Ph.D.)--Auburn University, 2008. / Abstract. Vita. Includes bibliographic references (p.176-181).

Thesis (M.H.A.)--University of Michigan, 1958.

Thesis (Ph. D.)--University of Missouri-Columbia, 1996. / Typescript. Vita. Includes bibliographical references (leaves 237-256). Also available on the Internet.