In studying natural history of a disease, incident studies provide the best quality estimates; in contrast, prevalent studies introduce a sampling bias, which, if the onset time of the disease follows a stationary Poisson process, is called length bias. When both types of data are available, combining the samples under the assumption that failure times in incident and prevalent cohorts come from the same distribution function, could improve the estimation process from a revalent sample. We verify this assumption using a Smirnov type of test and construct a likelihood function from a combined sample to parametrically estimate the survival through maximum likelihood approach. Finally, we use Accelerated Failure Time models to compare the effect of covariates on survival in incident, prevalent, and combined populations. Properties of the proposed test and the combined estimator are assessed using simulations, and illustrated with data from the Canadian Study of Health and Aging.

Network structure plays a significant role in determining the performance of network inference tasks. An interactive tool to study the dependence of network topology on estimation performance was developed. The tool allows end-users to easily create and modify network structures and observe the performance of pole estimation measured by Cramer-Rao bounds. The tool also automatically suggests the best measurement locations to maximize estimation performance, and thus finds its broad applications on the optimal design of data collection experiments. Finally, a series of theoretical results that explicitly connect subsets of network structures with inference performance are obtained.

Over the past 40 years limited progress has been made to help practitioners estimate the risk and the required effort necessary to deliver software solutions. Recent developments improve this outlook, one in particular, the research of Juan Carlos Nogueira. Dr. Nogueira developed a formal model for risk assessment that can be used to estimate a software projectαs risk when examined against a desired development time-line. Dr. Nogueira developed his model based on data collected from a series of experiments conducted on the ViteÌ Project simulation. This unique approach provides a starting point towards a proven formal model for risk assessment. Another issue with software development, especially in the Department of Defense (DoD), is dealing with aging legacy software systems. These systems perform the functionality of their design, but their interfaces are obsolete and changing requirements limit their functional usefulness. This thesis is an exercise in upgrading a legacy system licensed to the DoD, ViteÌ Project, for use with ongoing DoD research that seeks to discern truly quantifiable criteria that can be used to more accurately estimate the length of time needed to complete any software project. Accurately projecting software development times and accurate software development costs have eluded software developers for decades. / US Navy (USN) author

This thesis examines the context effects on retrieval, and the influence of action on the representation of distance in cognitive maps. It is proposed that bias in distance estimation is a function of the contexts of retrieval that trigger the representation of action in memory during evaluation tasks. The proposal is consistent with embodied cognition evidence that suggests that actions are implicitly a part of the representation, and will be naturally extracted as part of the retrieval process. The experimental work presented examines two different contextual cues; the frequency of visitation to landmarks, and the importance of activity performed at landmarks. Each cue primes differently the conceptualisation of landmarks prior to making distance estimation. This priming facilitates memory access, which fleshes out relevant spatial information from cognitive maps that are used in distance estimation and route description. This proposal was examined in a series of four experiments that employed structured interviews. Participants had to rate landmarks based on frequency of visitation criteria or importance of activity criteria, or both. They then made verbal distance estimations and route descriptions. The results found implicate the involvement of action representation. The involvement of action in cognitive process was empirically investigated in three further experiments. A new methodology was developed featuring the use of a blindfold, linguistic descriptions, and control of actual movements. Blindfolded participants learned new environments through verbal descriptions by imagining themselves walking in time with the metronome beats. During turns, they were carefully moved. Following instructions, they performed an action at mid-route. Their memories for the newly learned environments were tested through recalls and measured again with the metronome beats. The results found were consistent with explanations based on network-map theory. They implicate attentional processes as an intrinsic part of the cognitive mechanism, and the strings of the network-map as the actual motor program that executes the movement. These results are discussed in relation to the nature of cognitive maps.

Thesis advisor: Arthur Lewbel / My dissertation is composed of three chapters. The first chapter is on the asymptotic trimming and rate adaptive inference for heavy-tail distributed estimators. The second chapter is about the identification of the Average Treatment Effect for a two threshold model. The last chapter is on the identification of the parameters of interest in a binary choice model with interactive effects. / Thesis (PhD) — Boston College, 2015. / Submitted to: Boston College. Graduate School of Arts and Sciences. / Discipline: Economics.

by Wai-yin Poon. / Bibliography: leaves 62-64 / Thesis (M.Ph.)--Chinese University of Hong Kong, 1985

by Yuen Wah-Kong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1980. / Bibliography: leaves 37-38.

by Kwok-leung Tsui. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1981. / Bibliography: leaves 39-41.

So-Kuen Chan. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1992. / Includes bibliographical references (leaves 99-102). / Chapter Chapter One --- Preview --- p.1 / Chapter Section 1 --- Introduction --- p.1 / Chapter Section 2 --- The Life Time Distribution --- p.4 / Chapter 2.1 --- Exponential Distribution --- p.5 / Chapter 2.2 --- Gamma Distribution --- p.6 / Chapter 2.3 --- Weibull Distribution --- p.7 / Chapter 2.4 --- Lognormal Distribution --- p.10 / Chapter Section 3 --- Nonparametric Inference for Geometric Process --- p.13 / Chapter 3.1 --- Test for Geometric Process --- p.13 / Chapter 3.2 --- Nonparametric Estimation Method --- p.17 / Chapter Section 4 --- Test for Distribution --- p.20 / Chapter 4.1 --- Graphical Method --- p.20 / Chapter 4.2 --- KS-test --- p.22 / Chapter 4.3 --- x2 GOF-test --- p.27 / Chapter 4.4 --- F-test (Exponential Dist.) --- p.28 / Chapter Chapter Two --- Parametric Inference for Geometric Process --- p.29 / Chapter Chapter Three --- Simulations --- p.39 / Chapter Chapter Four --- Examples --- p.49 / Chapter Chapter Five --- Comparison and Conclusion --- p.57 / Tables and Graphs --- p.61 / References --- p.99

by Kwok-fai Lee. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1993. / Includes bibliographical references (leaves 85-86). / Chapter CHAPTER 1 --- INTRODUCTION --- p.1 / Chapter §1.1 --- Unequal probabilities sampling schemes without replacement --- p.1 / Chapter §1.2 --- Estimation Problems in unequal probabilities sampling scheme without replacement --- p.3 / Chapter §1.3 --- Classification of unequal probabilities sampling schemes without replacement --- p.5 / Chapter CHAPTER 2 --- ONE-PASS ALGORITHMS --- p.9 / Chapter §2.1 --- Characteristics of one-pass algorithms --- p.9 / Chapter §2.2 --- Existing one-pass algorithms --- p.10 / Chapter §2.2.1 --- Chao's one-pass algorithm / Chapter §2.2.2 --- Other algorithms / Chapter §2.3 --- Second order inclusion probabilities --- p.14 / Chapter CHAPTER 3 --- A NEW ONE-PASS ALGORITHM --- p.17 / Chapter §3.1 --- Introduction --- p.17 / Chapter §3.2 --- Examination of all possible cases --- p.20 / Chapter §3.3 --- Initialization --- p.57 / Chapter §3.4 --- Final step --- p.61 / Chapter §3.5 --- Theorems --- p.64 / Chapter §3.6 --- Worked example --- p.76 / Chapter CHAPTER 4 --- CONCLUSION --- p.83 / References --- p.85