No description available.

Despite considerable advances in missing data imputation methods over the last three decades, the problem of missing data remains largely unsolved. Many techniques have emerged in the literature as candidate solutions. These techniques can be categorised into two classes: statistical methods of data imputation and computational intelligence methods of data imputation. Due to the longstanding use of statistical methods in handling missing data problems, it takes quite some time for computational intelligence methods to gain profound attention even though these methods have analogous accuracy, in comparison to other approaches. The merits of both these classes have been discussed at length in the literature, but only limited studies make significant comparison to these classes. This thesis contributes to knowledge by firstly, conducting a comprehensive comparison of standard statistical methods of data imputation, namely, mean substitution (MS), regression imputation (RI), expectation maximization (EM), tree imputation (TI) and multiple imputation (MI) on missing completely at random (MCAR) data sets. Secondly, this study also compares the efficacy of these methods with a computational intelligence method of data imputation, ii namely, a neural network (NN) on missing not at random (MNAR) data sets. The significance difference in performance of the methods is presented. Thirdly, a novel procedure for handling missing data is presented. A hybrid combination of each of these statistical methods with a NN, known here as the post-processing procedure, was adopted to approximate MNAR data sets. Simulation studies for each of these imputation approaches have been conducted to assess the impact of missing values on partial least squares structural equation modelling (PLS-SEM) based on the estimated accuracy of both structural and measurement parameters. The best method to deal with particular missing data mechanisms is highly recognized. Several significant insights were deduced from the simulation results. It was figured that for the problem of MCAR by using statistical methods of data imputation, MI performs better than the other methods for all percentages of missing data. Another unique contribution is found when comparing the results before and after the NN post-processing procedure. This improvement in accuracy may be resulted from the neural network's ability to derive meaning from the imputed data set found by the statistical methods. Based on these results, the NN post-processing procedure is capable to assist MS in producing significant improvement in accuracy of the approximated values. This is a promising result, as MS is the weakest method in this study. This evidence is also informative as MS is often used as the default method available to users of PLS-SEM software.

This dissertation analyzes the language used by 20 adult heritage Welsh speakers now living in London, i.e., bilinguals who shifted to English dominance in childhood, and whose Welsh proficiencies now show divergences from baseline norms as a result of incomplete acquisition and attrition. The grammars of these heavily imbalanced bilinguals are compared with baseline informants (20 Welsh-dominant controls) on a narrative elicitation task, in which the informants tell the story of a children's wordless picture book (Frog, Where Are You? by Mercer Mayer). The samples collected for this project (Appendix II.1) constitute the first corpus of heritage Welsh. / Celtic Languages and Literatures

Technology trends toward lower power, higher speed and higher density devices have pushed the package performance to its limits. The high frequency effects e.g., crosstalk and signal distortion, may cause high bit error rates or malfunctioning of the circuit. Therefore, the successful release of a new product requires constant attention to the high frequency effects through the whole design process. Full-wave electromagnetic tools must be used for this purpose. Unfortunately, currently available full-wave tools require excessive computational resources to simulate large-scale interconnect structures.A prototype version of the Full-Wave Layered-Interconnect Simulator (UA-FWLIS), which employs the Method of Moments (MoM) technique, was developed in response to this design need. Instead of using standard numerical integration techniques, the MoM reaction elements were analytically evaluated, thereby greatly improving the computational efficiency of the simulator. However, the expansion and testing functions that are employed in the prototype simulator involve filamentary functions across the wire. Thus, many problems cannot be handled correctly. Therefore, a fundamental extension is made in this dissertation to incorporate rectangular-based, finite-width expansion and testing functions into the simulator. The critical mathematical issues and theoretical issues that were met during the extension are straightened out. The breakthroughs that were accomplished in this dissertation lay the foundation for future extensions. A new bend-cell expansion function is also introduced, thus allowing the simulator to handle bends on the interconnects with fewer unknowns. In addition, the Incomplete Lipschitz-Hankel integrals, which are used in the analytical solution, are studied. Two new series expansions were also developed to improve the computational efficiency and accuracy.

Incomplete data represents a major challenge for a successful prediction and subsequent removal of multiples. In this paper, a new method will be represented that tackles this challenge in a two-step approach. During the first step, the recenly developed curvelet-based recovery by sparsity-promoting inversion (CRSI) is applied to the data, followed by a prediction of the primaries. During the second high-resolution step, the estimated primaries are used to improve the frequency content of the recovered data by combining the focal transform, defined in terms of the estimated primaries, with the curvelet transform. This focused curvelet transform leads to an improved recovery, which can subsequently be used as input for a second stage of multiple prediction and primary-multiple separation.

Violeta Chiumakova. Theme of the Master of Science work: “Incomplete families 5-7 years old child education and competence peculiarity.” The research adviser of the work is – doc. dr. V. Glebuviene. The pedagogical university of Vilnius, The department of childhood studies, 2005. The empiric research of education and competence peculiarity, took place in Vilnius, Zarasai and Shalchininkai cities between 5-7 years old children from complete and incomplete families.155 children from incomplete families (ostensible group) and 247 children from complete families (control group) took part in the research. The aim of the research was to find out whether children from incomplete families competence abilities level differs from the children with complete family. Also was looking forward to find out how the family structure influences children’s education and competence abilities. Pedagogical, psychological, science literature analyzes were used for the Master of Science work; interview (conversation with child), collision situation, problem situation, observation, experiment, questionnaire for parents, questionnaire for pedagogues, processing methods for statistic information. While analyzing literature had become clear that because the lack of researches, it is very hard to answer the question, how does the child should be educated in school and kindergarten, if he lives in incomplete family. Neither educational standard, neither other recommendations can’t be generalized in this... [to full text]

Emanating from classical Weibull mixture models we propose a framework for clustering survival data with various proportionality restrictions imposed. By introducing mixtures of Weibull proportional hazards models on a multivariate data set a parametric cluster approach based on the EM-algorithm is carried out. The problem of non-response in the data is considered. The application example is a real life data set stemming from the analysis of a world-wide operating eCommerce application. Sessions are clustered due to the dwell times a user spends on certain page-areas. The solution allows for the interpretation of the navigation behavior in terms of survival and hazard functions. A software implementation by means of an R package is provided. (author´s abstract) / Series: Research Report Series / Department of Statistics and Mathematics

This thesis consists of five scientific papers dealing with equations related to the optimal switching problem, mainly backward stochastic differential equations and variational inequalities. Besides the scientific papers, the thesis contains an introduction to the optimal switching problem and a brief outline of possible topics for future research. Paper I concerns systems of variational inequalities with operators of Kolmogorov type. We prove a comparison principle for sub- and supersolutions and prove the existence of a solution as the limit of solutions to iteratively defined interconnected obstacle problems. Furthermore, we use regularity results for a related obstacle problem to prove Hölder continuity of this solution. Paper II deals with systems of variational inequalities in which the operator is of non-local type. By using a maximum principle adapted to this non-local setting we prove a comparison principle for sub- and supersolutions. Existence of a solution is proved using this comparison principle and Perron's method. In Paper III we study backward stochastic differential equations in which the solutions are reflected to stay inside a time-dependent domain. The driving process is of Wiener-Poisson type, allowing for jumps. By a penalization technique we prove existence of a solution when the bounding domain has convex and non-increasing time slices. Uniqueness is proved by an argument based on Ito's formula. Paper IV and Paper V concern optimal switching problems under incomplete information. In Paper IV, we construct an entirely simulation based numerical scheme to calculate the value function of such problems. We prove the convergence of this scheme when the underlying processes fit into the framework of Kalman-Bucy filtering. Paper V contains a deterministic approach to incomplete information optimal switching problems. We study a simplistic setting and show that the problem can be reduced to a full information optimal switching problem. Furthermore, we prove that the value of information is positive and that the value function under incomplete information converges to that under full information when the noise in the observation vanishes.

Following [10] we continue the study of the problem of expected utility maximization in incomplete markets. Our goal is to find minimal conditions on a model and a utility function for the validity of several key assertions of the theory to hold true. In [10] we proved that a minimal condition on the utility function alone, i.e. a minimal market independent condition, is that the asymptotic elasticity of the utility function is strictly less than 1. In this paper we show that a necessary and sufficient condition on both, the utility function and the model, is that the value function of the dual problem is finite. (authors' abstract) / Series: Working Papers SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Widespread species that occupy continents and oceanic islands provide an excellent opportunity to study evolutionary forces responsible for population divergence. Here, I use multilocus coalescent based population genetic and phylogenetic methods to infer the evolutionary history of the common chaffinch (Fringilla coelebs), a widespread Palearctic passerine species. My results showed strong population structure between Atlantic islands. However, the two European subspecies can be considered one panmictic population based on gene flow estimates. My investigation of effects of sampling on concatenated and Bayesian estimation of species tree (BEST) methods demonstrated that concatenation is more sensitive to sampling than BEST. Furthermore, concatenation can provide incorrect evolutionary relationships with high confidence when sample size is small. In conclusion, my results suggest European ancestry for the common chaffinch and Atlantic islands appear to have been colonized sequentially from north to south via Azores.