published_or_final_version / Statistics and Actuarial Science / Doctoral / Doctor of Philosophy

No description available.

Approved for public release, distribution is unlimited / "This work accomplishes signal denoising using the Bootstrap method when the additive noise is Gaussian. The noisy signal is separated into frequency bands using the Fourier or Wavelet transform. Each frequency band is tested for Gaussianity by evaluating the kurtosis. The Bootstrap method is used to increase the reliability of the kurtosis estimate. Noise effects are minimized using a hard or soft thresholding scheme on the frequency bands that were estimated to be Gaussian. The recovered signal is obtained by applying the appropriate inverse transform to the modified frequency bands. The denoising scheme is tested using three test signals. Results show that FFT-based denoising schemes perform better than WT-based denoising schemes on the stationary sinusoidal signals, whereas WT-based schemes outperform FFT-based schemes on chirp type signals. Results also show that hard thresholding never outperforms soft thresholding, at best its performance is similar to soft thresholding."--p.i. / First Lieutenant, Turkish Army

Kwok Kin On. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 49-51). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Collapsibility of the multidimensional table --- p.1 / Chapter 1.2 --- Bootstrap Method --- p.4 / Chapter 1.3 --- Scope of the thesis --- p.6 / Chapter 2 --- Testing Collapsibility using traditional asymptotic testing procedure --- p.7 / Chapter 2.1 --- Dimensional reduction in R x C x K contingency table --- p.7 / Chapter 2.2 --- Odd ratio --- p.9 / Chapter 2.3 --- Three types of collapsibility --- p.11 / Chapter 2.3.1 --- Strict Collapsibility --- p.11 / Chapter 2.3.2 --- Strong Collapsibility --- p.12 / Chapter 2.3.3 --- Pseudo Collapsibility --- p.14 / Chapter 2.4 --- Setup of the testing procedure of collapsibility --- p.15 / Chapter 2.5 --- Asymptotic testing procedure of strict collapsibility --- p.16 / Chapter 2.6 --- Asymptotic testing procedure of pseudo collapsibility --- p.18 / Chapter 3 --- Testing Collapsibility using bootstrapping method --- p.20 / Chapter 3.1 --- Motivation of using bootstrap method --- p.20 / Chapter 3.2 --- Bootstrapping method --- p.20 / Chapter 3.3 --- Bootstrapping test procedure --- p.24 / Chapter 3.4 --- Test statistics --- p.27 / Chapter 3.4.1 --- Test statistics for strict collapsibility --- p.27 / Chapter 3.4.2 --- Test statistics for pseudo collapsibility --- p.29 / Chapter 4 --- Results --- p.31 / Chapter 4.1 --- Type I error rate of two tests --- p.31 / Chapter 4.1.1 --- Type I error rate of two tests for strict collapsibility --- p.31 / Chapter 4.1.2 --- Type I error rate of two tests for pseudo collapsibility --- p.35 / Chapter 4.2 --- Power of the two tests --- p.37 / Chapter 4.2.1 --- Power of two tests for strict collapsibility --- p.38 / Chapter 4.2.2 --- Power of two tests for pseudo collapsibility --- p.41 / Chapter 4.3 --- Application to Simpson's Paradox data --- p.45 / Chapter 4.3.1 --- Comparison of two tests for strict collapsibility on Simpson's Paradox data --- p.45 / Chapter 4.3.2 --- Comparison of two tests for strict collapsibility on Simpson's Paradox data --- p.46 / Chapter 4.4 --- Conclusion --- p.47 / Reference --- p.49-51

Three high speed circuit schemes for a low supply voltage DRAM are presented in this thesis. First, a high drivability bootstrapped word line driver is proposed. We use one boosting circuit collocating an NMOS to serve as the pulling up device rather than a PMOS to increase the current driving ability of the output stage. When the driving loading is 512 memory cells with the supply voltage of 1.5V, the switching time of the proposed word line driver is 1.13ns faster than that of the conventional one, the switching speed of the word line is 31.1% improved. Second, a pulse-controlled overdriven sense amplifier (PCO-SA) is proposed. We can make use of the pulse width of a pulse generator to control the overdriven time of the sensing transistors thereby enlarging the VGS of the sensing transistors transiently and improving the sensing speed. The sensing speed of the PCO-SA is 4.4ns faster than that of conventional sense amplifier with the supply voltage of 1.5V, the sensing time is 34.1% improved. In addition, even if the supply voltage is decreased to 1.3V, the function of the PCO-SA still correctly, whereas conventional sense amplifier cannot. Third, a modified N&PMOS cross-coupled main amplifier is presented. We make the charging path of speedy circuit which has the ability of passing the full VDD voltage to the input of the second stage. By this way, the data read out speed of the modified main amplifier is 5.87ns faster than that of the conventional N&PMOS cross-coupled main amplifier, the data read out time is 30.4% improved. Finally, three proposed circuits in this thesis are integrated and examined in a 1-Kbit DRAM test circuit. The simulated RAS access time of 28.9ns is achieved with the supply voltage of 1.5V, the RAS access time is 16% improved. These also indicate that the proposed circuit schemes are suitable for application in a low supply voltage DRAM.

published_or_final_version / Statistics and Actuarial Science / Master / Master of Philosophy

The bootstrap methods are widely used for constructing confidence intervals. However, the conventional bootstrap fails to be consistent under some nonstandard circumstances. The m out of n bootstrap is usually adopted to restore consistency, provided that a correct convergence rate can be specified for the plug-in estimators. In this thesis, we re-investigate the asymptotic properties of the bootstrap in a moving-parameter framework in which the underlying distribution is allowed to depend on n. We consider the problem of setting uniformly consistent confidence intervals for two non-regular cases: (1) the smooth function models with vanishing derivatives; and (2) the M-estimation with non-regular conditions. Under the moving-parameter setup, neither the conventional bootstrap nor the m out of n bootstrap is shown uniformly consistent over the whole parameter space. The results reflect to some extent finite-sample anomalies that cannot be explained by conventional, fixed-parameter, asymptotics. We propose a weighted bootstrap procedure for constructing uniformly consistent bootstrap confidence intervals, which does not require explicit specification of the convergence rate of the plug-in estimator. Under the smooth function models, we also propose a modified n out of n bootstrap procedure in special cases where the smooth function is applied to estimators that are uniformly bootstrappable. The estimating function bootstrap is also successfully employed for the latter model and enjoys computational advantages over the weighted bootstrap. We illustrate our findings by comparing the finite-sample coverage performances of the different bootstrap procedures. The stable performance of the proposed methods, contrasts sharply with the erratic coverages of the n out of n and m out of n bootstrap intervals, a result in agreement with our theoretical findings. / published_or_final_version / Statistics and Actuarial Science / Master / Master of Philosophy

In statistical inference, one is often interested in estimating the distribution of a root, which is a function of the data and the parameters only. Knowledge of the distribution of a root is useful for inference problems such as hypothesis testing and the construction of a confidence set. Shrinkage-type estimators have become popular in statistical inference due to their smaller mean squared errors. In this thesis, the performance of different bootstrap methods is investigated for estimating the distributions of roots which are constructed based on shrinkage estimators. Focus is on two shrinkage estimation problems, namely the James-Stein estimation and the model selection problem in simple linear regression. A hybrid bootstrap procedure and a bootstrap test method are proposed to estimate the distributions of the roots of interest. In the two shrinkage problems, the asymptotic errors of the traditional n-out-of-n bootstrap, m-out-of-n bootstrap and the proposed methods are derived under a moving parameter framework. The problem of the lack of uniform consistency of the n-out-of-n and the m-out-of-n bootstraps is exposed. It is shown that the proposed methods have better overall performance, in the sense that they yield improved convergence rates over almost the whole range of possible values of the underlying parameters. Simulation studies are carried out to illustrate the theoretical findings. / published_or_final_version / Statistics and Actuarial Science / Master / Master of Philosophy

published_or_final_version / abstract / toc / Statistics and Actuarial Science / Master / Master of Philosophy

No description available.