国立情報学研究所で電子化したコンテンツを使用している。

Thesis (M.S.)--Ohio University, June, 1997. / Title from PDF t.p.

Thesis (M. Soc. Sc.)--University of Hong Kong, 1993. / Includes bibliographical references (leaves 79-80).

Thesis (Ph. D.)--University of Michigan, 1934. / Lithoprinted. "Reprinted from the Annals of Mathematical Statistics, November, 1933."

Thesis (M.Soc.Sc.)--University of Hong Kong, 1993. / Includes bibliographical references (leaves 79-80) Also available in print.

Recrystallised alumina is used as a high performance crucible material. Its thermal shock resistance is known to be affected by component shape, and also by processing variables, since the defects and internal stress at both the microscale (i.e. between grains due to anisotropic crystal properties) and macroscale (i.e. due to differential shrinkage during sintering) influence the fracture strength. The aim of this thesis is to study the nucleation and growth of defects in pure alumina and Cr-doped alumina, and to investigate how their behavior is affected by residual stresses, such those introduce by thermal expansion of the crystal grains. In this thesis, digital image correlation is applied to polycrystalline aluminas (i.e. Cr-doped alumina and pure alumina with average grain 3.6 µm and 1.5 µm respectively) that are stressed in an optical microscope. The defect size and the surface crack opening displacement were measured using digital image correlation. The distribution and population of crack nucleating defects were obtained by in-situ observation of the stressed surface and by analysis with digital image correlation. These data are then compared with independent measurements of the defect population using Hertzian indentation, from which defect populations are derived for the pure and Cr-doped alumina samples. Grain boundary plane and grain orientations in the vicinity of crack nuclei were characterised by electron microscopy. Crack nuclei were shown to develop at boundaries predicted to have high tensile thermal strains, caused by the orientation of the grain boundary plane relative to the adjacent grains, such as basal plane grain facets. The techniques of focused ion beam (FIB) milling and electron backscatter diffraction (EBSD) characterization of the crystallographic orientations and structure of cracked grain boundaries were used to provide data for a model to explain the cracking of these boundaries as a result of the thermal strains and the anisotropic thermal expansion behaviour of alumina.

Not only basic research in sciences, but also medicine, law, and manufacturing need statistical techniques, including graphics, to assess disagreement. For some items or individuals ⍳ = 1,2,---,ո suppose that pairs (X⍳,Y⍳) denote each item's measurements by two distinct methods or by two observers, or X⍳ and Y⍳ may be initial and repeat measurement scores, with discrepancy D⍳ = X⍳ - Y⍳. Disagreement may be characterized by location and scale parameters of discrepancy distributions. The present work primarily addresses estimation of central tendency - relative bias or median discrepancy (or discrepancy rate in some instances). Most previous literature on "agreement" or "reliability" instead concerns X, Y correlation, which can be regarded as the complement of discrepancy variance. (There is ambiguity or confusion about concepts of "reliability" in the literature of various applications.) Discrepancies D₁, D₂, • • •, Dո in practice often violate assumptions of standard statistical models and methods that have been commonly applied in studies of agreement. In particular, both X⍳ and Y⍳ generally incorporate measurement errors. Further, these two measurement error distributions for the ⍳th item need not be the same; and both distributions could depend on the magnitude µ⍳, of the item being measured. Hence, for example, discrepancy D⍳ could have variance proportional to the size of the item; and in general D₁, D₂, • • •, Dո are not identically distributed. Finally, the selection of items ⍳ = 1,2, • • •, ո often is not random. To estimate median discrepancy, we consider nonparametric confidence intervals corresponding to Student t test, sign test, Wilcoxon signed rank test, or other permutation tests. Several criteria are developed to compare the performance of one procedure relative to another, including expected ratio of confidence interval lengths (related to Pitman asymptotic relative efficiency of tests) and relative variability of interval lengths. Theoretical calculations and Monte Carlo simulation results suggest different procedural preferences for random sampling from different distributions. For discrepancies distributed non-identically, but symmetrically about a common median value, mixture sampling is used as an approximate model. This approach is related to a "random walk" (rather than random sample) model of D₁, D₂, • • •, Dո proposed particularly for discrepancies between counting processes. We also emphasize graphic methods, especially plots of difference of Y - X versus average (X + Y)/2, for exploratory analysis of discrepancy data and to choose appropriate statistical models and numerical methods. Various data sets are analyzed as examples of the methodology. / Science, Faculty of / Statistics, Department of / Graduate

Gasoline is a complex fuel containing hundreds of species, and, therefore, it is quite difficult to model all components present in gasoline. Alternatively, researchers tend to employ simpler surrogates that mimic targeted physical and chemical properties of gasoline. Two properties of gasoline, i.e., autoignition and laminar flame speed, play key role in the overall performance of spark-ignition and modern engines. For fuel-engine optimization, it is very important to have simple models which can accurately predict autoignition and laminar flame speed of gasoline. In this work, universal laminar flame speed correlation is proposed for typical gasolines. This correlation is based on Monte-Carlo simulations of randomly generated mixtures comprising of 21 gasoline-relevant molecules. Laminar flame speed of each molecule is numerically computed over a wide range of thermodynamic conditions using detailed chemical kinetic models, while flame speed of each mixture is estimated using a mixing rule. The proposed universal correlation is validated against experimentally-measured laminar flame speed of various gasoline fuels.

Bibliography: p. 178-182. / The purpose of this thesis is to provide a study of the linear model. The whole work has been split into 6 chapters. In Chapter 1 we define and examine the two linear models, i.e. the regression and the correlation model. More specifically we show that the regression model is the conditional version of the correlation model. In Chapter 2 we deal with the problem of multicollinearity. We investigate the sources of near singularities, we give some methods of detecting the multicollinearity, and we state briefly methods for overcoming this problem. In Chapter 3 we consider the least squares method with restrictions, and we dispose of some tests for testing the linear restrictions. The theory concerning the sign of least squares estimates is discussed, then we deal with the method for augmenting existing data. Chapter 4 is mainly devoted to ridge regression. We state methods for selecting the best estimate for k. Some extensions are given dealing with the shrinkage estimators and the linear transforms of the least squares. In Chapter 5 we deal with the principal components, and we give methods for selecting the best subset of principal components. Much attention was given to a method called fractional rank and latent root regression analysis. In Chapter 6 comparisons were performed between estimators previously mentioned. Finally the conclusions are stated.

Diffusion MRI is established as an essential tool for both clinicians as well as biomedical scientists. Its application plays an important role in diagnosis and management of acute stroke, tumors, trauma, and infectious disease, among myriad other applications. Furthermore, diffusion studies are crucial for understanding disease processes caused by developmental and neurodegenerative disorders. The latest developments in quantitative diffusion imaging have broadened the potential application of the technique for both clinical and research applications. However, ongoing research is critical in order to further improve the accuracy and reproducibility of quantitative diffusion MRI techniques. Correlation time diffusion (D-CT) is emerging as an alternative technique for obtaining diffusion qMRI data[1][2][3]. Using the D-CT technique, T1 relaxation data is analyzed, using a modified BPP relaxation theory, in order to calculate the correlation times of protons’ stochastic processes and relate these times to solution viscosity in order to calculate proton diffusion coefficients, ADCs. The purpose of our study was to compare age related changes, during childhood and early adulthood, of global brain diffusion coefficients obtained by correlation time technique to global brain diffusion coefficients obtained by a conventional pulsed field gradient technique. In our study, we used the data of 27 subjects (0.5-24 years old), who were scanned with Mixed-TSE and DW-SS-SE-EPI pulse sequences. Subsequently, we processed the resulting directly acquired images to generate T1, T2, PD, ADC maps as well as volumetric data. We used the student t-test and linear regression analysis to compare and interpret our data. Our results show a strong positive correlation between the volumetric data. Good correlation between ADC values was observed, with the widest discrepancy between DCT, DPFG (about 17%) observed in the youngest subjects, and the smallest discrepancy noted in the older subjects.