Age estimation is a critical component of the biological profile in forensic and bioarchaeological contexts. The majority of age estimation methods are most accurate for individuals of younger age cohorts, typically those under 40 years of age. Skeletal degeneration can vary greatly between individuals, making age estimation less accurate for adult individuals. While there are some methods that attempt to age older individuals accurately and precisely, more research must be conducted to expand the range of methods available. Falys and Prangle (2014) developed a method for estimating age in individuals over the age of 40 using three degenerative characteristics of the sternal end of the clavicle: (1) surface topography, (2) porosity, and (3) osteophyte formation. In order to test their method, a sample of 1,510 individuals of known sex and age, ranging from 20 to 101 years of age (males: n = 1112, mean = 50.57, SD = 18.015; females: n = 398, mean = 53.065, SD = 20.358), were drawn from the McCormick Collection and the William M. Bass Donated Skeletal Collection at the University of Tennessee. Due to the paucity of remains of other ancestries, only individuals of reported White ancestry were used in this study. The two estimation methods proposed in Falys and Prangle (2014), regression equation and composite score, were tested to see how well they perform when applied to a different sample population than the populations used to develop the method. When applied to the collected data, the regression equation produced age estimations that fell within the 95% confidence interval in 47.6% of the male sample and 57.4% of the female sample. Composite scores were calculated and compared to the corresponding age ranges provided in Falys and Prangle (2014). The composite scores of the male sample estimated the age of an individual more accurately than the composite scores of the female sample (male = 65.9%; female = 58.8%). The lowest estimation accuracy for both males and females was between 70-79 years of age (male = 46.0%; female = 51.4%). From 80-89 years of age, the accuracy increased for males (76.4%) and females (69.4%). The sample also included individuals under the age of 40 in order to test whether the inclusion of clavicles with recent epiphyseal union would affect the applicability of the Falys and Prangle (2014) method. Multiple regression equations were generated: (1) individuals over 20 years of age, (2) individuals over 30 years of age, and (3) individuals over 40 years of age. The results from the multiple regression analyses show comparable Pearson’s coefficients for the above mentioned equations (r = 0.690, r = 0.632, and r = 0.611, respectively). Spearman’s rank correlation coefficients indicated a correlation significant at the 0.01 level for all three components individually, as well as the composite score. Of the three components, surface topography was most strongly correlated with age for both males (r = 0.643) and females (r = 0.590). Unlike the findings of Falys and Prangle (2014), porosity was found to be the least correlated with age for both males (r = 0.474) and females (r = 0.514). In addition, when broken down into ten year intervals (40-49, 50-59, etc.), the correlation coefficients increase with advancing age. This suggests that the method becomes more accurate as the age of an individual increases. The inter-observer and intra-observer agreement tests produced very low agreement values. The low observer agreement indicates that the current scoring method is not a reliable, repeatable technique. However, when examined further, the observed trait values that differed between the tests primarily differed by one score. These results suggest that condensing the scores in order to account for more variation would likely increase the observer agreement. However, condensing the scores would result in larger age intervals, which nullifies the purpose of this method. The findings in the present study indicate that the sternal end of the clavicle has potential for use in age estimation in older individuals. Although the present study produced lower correlation coefficients than proposed by the original study in 2014, the correlations and age-at-transition test results suggest that the sternal end of the clavicle deteriorates in a predictable manner that, with more observation and understanding, could be used to accurately age older individuals more precisely than the large age intervals currently in use. Despite the correlations between the degeneration of the sternal end of the clavicle and the age-at-death, the error rates suggest it is not a reliable alternative to the current methods used.

Latent variables are often included in a model in order to capture the diversity among subjects in a population. Sometimes the distribution of these latent variables are of principle interest. In studies where sequences of observations are taken from subjects, ancillary variables, such as the number of observations provided by each subject, usually also vary between subjects. The goal here is to understand efficient estimation of the expectation of the latent variable in the presence of these subject-specific ancillaries. Unbiased estimation and efficient estimation of the expectation of the latent parameter depend on the dependence structure of these three subject-specific components: latent variable, sequence of observations, and ancillary. This dissertation considers estimation under two dependence configurations. In Chapter 3, efficiency is studied under the model in which no assumptions are made about the joint distribution of the latent variable and the subject-specific ancillary. Chapter 4 treats the setting where the ancillary variable and the latent variable are independent.

This thesis focuses on estimation and inference for a large class of semiparametric estimands: the class of continuous functionals of regression functions. This class includes a number of estimands derived from causal inference problems, among then the average treatment effect for a binary treatment when treatment assignment is unconfounded and many of its generalizations for non-binary treatments and individualized treatment policies. Chapter 2, based on work with Stefan Wager, introduces the augmented minimax linear es- timator (AMLE), a general approach to the problem of estimating a continuous linear functional of a regression function. In this approach, we estimate the regression function, then subtract from a simple plug-in estimator of the functional a weighted combination of the estimated regression function’s residuals. For this, we use weights chosen to minimize the maximum of the mean squared error of the resulting estimator over regression functions in a chosen neighborhood of our estimated regression function. These weights are shown to be a universally consistent estimator our linear functional’s Riesz representer, the use of which would result in an exact bias correction for our plug- in estimator. While this convergence can be slow, especially when the Riesz representer is highly nonsmooth, the action of these weights on functions in the aforementioned neighborhood imitates that of the Riesz representer accurately even when they are slow to converge in other respects. As a result, we show that under no regularity conditions on the Riesz representer and minimal regularity conditions on the regression function, the proposed estimator is semiparametrically efficient. In simulation, it is shown to perform very well in the context of estimating the average partial effect in the conditional linear model, a simultaneous generalization of the average treatment effect to address continuous-valued treatments and of the partial linear model to address treatment effect heterogeneity. Chapter 3, based on work with Arian Maleki and José Zubizarreta, studies the minimax linear estimator, a simplified version of the AMLE in which the estimated regression function is taken to be zero, for a class of estimands generalizing the mean with outcomes missing at random. We show semiparametric efficiency under conditions that are only slightly stronger than those required for the AMLE. In addition, we bound the deviation of our estimator’s error from the averaged efficient influence function, characterizing the degree to which the first order asymptotic characterization of semiparametric efficiency is meaningful in finite samples. In simulation, this estimator is shown to perform well relative to alternatives in high-noise, small-sample settings with limited overlap between the covariate distribution of missing and nonmissing units, a setting that is challenging for approaches reliant on accurate estimation of either or both of the regression function and the propensity score. Chapter 4 discusses an approach to rounding linear estimators for the targeted average treatment effect into matching estimators. The targeted average treatment effect is a generalization of the average treatment effect and the average treatment effect on the treated units.

Yim Tsz-ho. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2003. / Includes bibliographical references (leaves 47-49). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Local Polynomial Modeling --- p.4 / Chapter 2.1 --- Local Polynomial Fitting --- p.4 / Chapter 2.1.1 --- Methodology --- p.4 / Chapter 2.1.2 --- The kernel K --- p.6 / Chapter 2.1.3 --- The bandwidth h --- p.7 / Chapter 2.1.4 --- The order p --- p.10 / Chapter 2.2 --- Estimation of Conditional Density --- p.11 / Chapter 3 --- Bandwidth Selection --- p.14 / Chapter 3.1 --- Rule of Thumb --- p.14 / Chapter 3.2 --- Bootstrap Bandwidth Selection --- p.15 / Chapter 3.3 --- A Cross-Validation Method --- p.16 / Chapter 4 --- A Theoretical Justification --- p.18 / Chapter 4.1 --- Proof of (4.1) --- p.19 / Chapter 4.2 --- Proof of (4.2) --- p.22 / Chapter 5 --- Simulation Studies --- p.25 / Chapter 6 --- Real Data Applications --- p.38 / Chapter 6.1 --- Case Study With Canadian Lynx Data.............................. --- p.38 / Chapter 6.2 --- Case Study With U.S. Twelve-Month Treasury Bill Data.......... --- p.41 / Chapter 7 --- Conclusions --- p.45 / Bibliography --- p.47

En physique de l’atmosphère, la reconstruction d’une source polluante à partir des mesures de capteurs est une question importante. Elle permet en effet d’affiner les paramètres des modèles de dispersion servant à prévoir la propagation d’un panache de polluant, et donne aussi des informations aux primo-intervenants chargés d’assurer la sécurité des populations. Plusieurs méthodes existent pour estimer les paramètres de la source, mais leur application est coûteuse à cause de la complexité des modèles de dispersion. Toutefois, cette complexité est souvent nécessaire, surtout lorsqu’il s’agit de traiter des cas urbains où la présence d’obstacles et la météorologie instationnaire imposent un niveau de précision important. Il est aussi vital de tenir compte des différents facteurs d’incertitude, sur les observations et les estimations. Les travaux menés dans le cadre de cette thèse ont pour objectif de développer une méthodologie basée sur l’inférence bayésienne adaptative couplée aux méthodes de Monte Carlo pour résoudre le problème d’estimation du terme source. Pour cela, nous exposons d’abord le contexte scientifique du problème et établissons un état de l’art. Nous détaillons ensuite les formulations utilisées dans le cadre bayésien, plus particulièrement pour les algorithmes d’échantillonnage d’importance adaptatifs. Le troisième chapitre présente une application de l’algorithme AMIS dans un cadre expérimental, afin d’exposer la chaîne de calcul utilisée pour l’estimation de la source. Enfin, le quatrième chapitre se concentre sur une amélioration du traitement des calculs de dispersion, entraînant un gain important de temps de calcul à la fois en milieu rural et urbain. / In atmospheric physics, reconstructing a pollution source is a challenging but important question : it provides better input parameters to dispersion models, and gives useful information to first-responder teams in case of an accidental toxic release.Various methods already exist, but using them requires an important amount of computational resources, especially as the accuracy of the dispersion model increases. A minimal degree of precision for these models remains necessary, particularly in urban scenarios where the presence of obstacles and the unstationary meteorology have to be taken into account. One has also to account for all factors of uncertainty, from the observations and for the estimation. The topic of this thesis is the construction of a source term estimation method based on adaptive Bayesian inference and Monte Carlo methods. First, we describe the context of the problem and the existing methods. Next, we go into more details on the Bayesian formulation, focusing on adaptive importance sampling methods, especially on the AMIS algorithm. The third chapter presents an application of the AMIS to an experimental case study, and illustrates the mechanisms behind the estimation process that provides the source parameters’ posterior density. Finally, the fourth chapter underlines an improvement of how the dispersion computations can be processed, thus allowing a considerable gain in computation time, and giving room for using a more complex dispersion model on both rural and urban use cases.

Hung, King Chi. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references (leaves 78-52). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Non-linear Time Series Models and Their Applications --- p.2 / Chapter 1.2 --- The SETAR Model --- p.4 / Chapter 1.3 --- Objectives and Organization of the Thesis --- p.6 / Chapter 2 --- The SETAR Model and Robust Test for Non-linearity --- p.8 / Chapter 2.1 --- A Brief Review of Existing Tests for Threshold-type Non-linearity --- p.9 / Chapter 2.2 --- Robust Tests for Threshold-type Non-linearity --- p.11 / Chapter 2.2.1 --- Tsay´ةs F Test --- p.12 / Chapter 2.2.2 --- The Proposed Test --- p.15 / Chapter 2.3 --- The Choice of the ψ-function --- p.23 / Chapter 2.4 --- A Simulation Study --- p.26 / Chapter 2.4.1 --- Data Generation Process (DGP) --- p.26 / Chapter 2.4.2 --- Simulation Findings --- p.29 / Chapter 3 --- Robust Estimation and Asymptotic Properties --- p.34 / Chapter 3.1 --- Least Squares Estimation --- p.37 / Chapter 3.2 --- Robust Estimation --- p.38 / Chapter 3.2.1 --- Asymptotic Properties --- p.40 / Chapter 3.3 --- A Simulation Study --- p.52 / Chapter 3.3.1 --- Data Generation Process (DGP) --- p.53 / Chapter 3.3.2 --- Simulation Findings --- p.55 / Chapter 3.3.3 --- Objective Function over r --- p.56 / Chapter 4 --- Numerical Example --- p.67 / Chapter 4.1 --- Methodology --- p.68 / Chapter 4.2 --- ASEAN Background --- p.69 / Chapter 4.2.1 --- Non-linearity tests on ASEAN Exchange Rate --- p.72 / Chapter 4.2.2 --- Estimation of the Return of Singaporean Dollar --- p.73 / Chapter 5 --- Conclusions and Further Research --- p.76 / References --- p.78

L'estimation de canal est une tâche cruciale du récepteur dans les systèmes de communication sans fil, en particulier en cas de mobilité où les paramètres du canal varient avec le temps. Dans cette thèse, un nouvel estimateur de boucle de poursuite d'ordre 3 ( RW3-CATL), qui a une structure semblable à la PLL avec une faible complexité a été tout d'abord proposé pour estimer l'amplitude complexe du canal dans le cas mono-trajet mono-porteuse. Le lien entre un filtre de Kalman en régime asymptotique basé sur un modèle d'approximation de marche aléatoire (RW3-KF) et l'estimateur proposé est établi. Les expressions des paramètres sous-optimaux et d'EQM correspondante sont données sous forme analytiques en fonction des gains de boucle. Ensuite, les performances asymptotiques du RW3-KF ont été analysées en résolvant les équations de Riccati. L'expression analytique de la variance optimale du bruit d'état qui minimise l'EQM asymptotique a été également déduite. / Channel Estimation is a crucial task of the receiver in wireless communication systems, especially in case of mobility where the channel parameters vary with time. In this thesis, a novel PLL-structured third-order tracking loop estimator (RW3-CATL) with a low complexity is firstly proposed to estimate the complex amplitude of the channel in the mono-path single-carrier scenario. The connection between a steady-state Kalman filter based on a random walk approximation model (RW3-KF) and the proposed estimator has been established. The sub-optimal parameters and the corresponding MSE of the RW3-CATL are given in closed-form expressions in function of the tracking loop parameters. Then, the asymptotic performance of the RW3-KF has been analysed by solving the Riccati equations. The closed-form expression of the optimal state noise variance which minimizes the asymptotic MSE is also derived.

This thesis investigates whether estimating the inputs of the Markowitz (1952) Mean- Variance framework using various econometric techniques leads to improved optimal portfolio allocations at the country, sector and stock levels over a number of time periods. We build upon previous work by using various combinations of conventional and Bayesian expected returns and covariance matrix estimators in a Mean-Variance framework that incorporates a benchmark reference, an allowable deviation range from the benchmark weights and short-selling constraints so as to achieve meaningful and realistic outcomes. We found that models based on the classical maximum likelihood method performed just as well as the more sophisticated Bayesian return estimators in the study. We also found that the covariance matrix estimators analysed created covariance matrices that were similar to one another and, as a result, did not seem to have a large effect on the overall portfolio allocation. A sensitivity analysis on the level of risk aversion confirmed that the simulation results were robust for the different levels of risk aversion.

Telecommunication networks become major parts in modern complex control systems recently. They provide many advantages over conventional point-to-point connections, such as the simplification on installation and maintenance with comparatively low cost and the nature requirement of wireless communication in remote control systems. In practice, limited resource networks are shared by multiple controllers, sensors and actuators, and they may need to serve some other information unrelated to control purpose. Consequently, the control system design in networked control systems should be revised by taking communication constraints, for example, finite precision data, time delay and noise in transmission, into account. This thesis studies the robust control and state estimation of uncertain systems, when feedback information is sent via limited capacity communication channels. It focuses on the problem of finite precision data due to the communication constraints. The proposed schemes are based on the robust set-valued state estimation and the optimal control techniques. A state estimation problem of linear uncertain system is studied first. In this problem, we propose an algorithm called coder-decoder for uncertain systems. The coder encodes the observed output into a finite-length codeword and sends it to the decoder that generates the estimated state based on the received codeword. As an illustration, we apply the results in state estimation problem to a precision missile guidance problem using sensor fusion. In this problem, the information obtained from remote sensors is transmitted through limited capacity communication networks to the guided missile. Next, we study a stabilization problem of linear uncertain systems with state feedback. In this problem, the coder-controller scheme is developed to asymptotically stabilize the uncertain systems via limited capacity communication channels. The coder encodes the full state variable into a finite-length codeword and sends it to the controller that drives the system state to the origin. To achieve the asymptotic stability, we use a dynamic quantizer so that quantization noise converges to zero. The results in both state estimation and stabilization problems can handle the problem of finite data rate communication networks in control systems.

Thesis (M. Phil.)--University of Hong Kong, 2007. / Title proper from title frame. Also available in printed format.