Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2003. / Includes bibliographical references (leaves 55-58). Also available in electronic version. Access restricted to campus users.

Thesis (Ph. D.)--University of Wisconsin--Madison, 2003. / Includes bibliographical references (p. 104-107). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2003. / Typescript. Vita. Includes bibliographical references (leaves 84-88). Also available on the Internet.

Thesis (Ph. D.)--University of Hong Kong, 1984.

Thesis (Ph.D)--Mathematics, Georgia Institute of Technology, 2009. / Committee Chair: Bunimovich, Leonid; Committee Member: Bonetto, Federico; Committee Member: Chow, Shui-Nee; Committee Member: Cvitanovic, Predrag; Committee Member: Weiss, Howard. Part of the SMARTech Electronic Thesis and Dissertation Collection.

Thesis (Ph.D.)--University of Wisconsin. / Reprint of Bulletin 13 of the Bureau of the census (including original t.-p) Appendices: A. The adjustment of the returns.--B. Bibliography of discussions of age statistics. Includes bibliographical references. Also available in digital form on the Internet Archive Web site.

This study has been undertaken to determine what pseudo-proprietary information and patenting activity statistics could be derived from an online patents database. To achieve this, a thorough investigation uas made of patenting in the field of an important group of beta-lactam antibiotics, the. Cephalosporins. Patents data was retrieved from the World Patents Index online files of Derwent Publications Limited, and the bibliographic details of each patent application retrieved analysed according to numbers of patents per patentee, priority and publication dates, types of patents, etc. A review of technological advances in this subject was conducted, demonstrating the value of patents literature for such purposes. The relationship between sales volumes and patenting activity for Cephalosporins patentees has been investigated and found to show a. significant correlation between these parameters. As an extension, the USA patenting and sales activity for the leading USA Industrial Corporations (the 1981 Fortune 500) was studied; overall a high correlation was exhibited, but there were notable differences. between different industries. A number of bibliometric studies have been undertaken with a variety of patents data. for a number of techhologies. These studies include the application of Bradford-Zipf plots, other productivity studies and Vector Analysis to patents. Whilst previous studies on journal literature have investigated the applicability of frequency distributions as measures of author productivity, this study has for the first time applied Lotka's Law, Price's Pareto-type Distribution, Simon-Yule Distribution, Shockley's Lognormal Distribution, Borel-Tanner Distribution, Williams Geometric Series, Fisher's Logarithmic Series and the Negative Binomial Distribution to patents data. Theoretical distributions were ascertained using a series of microcomputer programs written in BASIC programming' language. The results indicate that of the distributions investigated, the Negative Binomial most closely fits the observed data when goodness-offit is measured by the Kolmogorov-Smirnov Test.

In fields across science and engineering, we are increasingly faced with problems where the number of variables or features we need to estimate is much larger than the number of observations. Under such high-dimensional scaling, for any hope of statistically consistent estimation, it becomes vital to leverage any potential structure in the problem such as sparsity, low-rank structure or block sparsity. However, data may deviate significantly from any one such statistical model. The motivation of this thesis is: can we simultaneously leverage more than one such statistical structural model, to obtain consistency in a larger number of problems, and with fewer samples, than can be obtained by single models? Our approach involves combining via simple linear superposition, a technique we term dirty models. The idea is very simple: while any one structure might not capture the data, a superposition of structural classes might. Dirty models thus searches for a parameter that can be decomposed into a number of simpler structures such as (a) sparse plus block-sparse, (b) sparse plus low-rank and (c) low-rank plus block-sparse. In this thesis, we propose dirty model based algorithms for different problems such as multi-task learning, graph clustering and time-series analysis with latent factors. We analyze these algorithms in terms of the number of observations we need to estimate the variables. These algorithms are based on convex optimization and sometimes they are relatively slow. We provide a class of low-complexity greedy algorithms that not only can solve these optimizations faster, but also guarantee the solution. Other than theoretical results, in each case, we provide experimental results to illustrate the power of dirty models. / text

The purpose of this report is to give teachers of AP Statistics a way to enrich student learning with an engaging, rigorous and relevant project. The report details the reasons necessary for student-based learning, along with examples in which projects in classrooms were successful. The project is centered on categorical data analysis involving tests of proportions, chi-squared distributions and confidence intervals. There are supplemental worksheets provided with the intent of showing students the relevance and applications of what they are learning to actual studies. Finally, a rubric is provided for students to align and focus their projects as well as for teachers to assess student learning. / text

published_or_final_version / Dentistry / Doctoral / Doctor of Philosophy