Efficient estimation using the characteristic function : theory and applications with high frequency data

The attached file is created with Scientific Workplace Latex

Statistical methods for insurance fraud detection

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal

Features of neighbourhood environments associated with obesity and related health behaviours in children: using multiple statistical approaches to identify obesogenic environments

Contexte: L'obésité chez les jeunes représente aujourd’hui un problème de santé publique à l’échelle mondiale. Afin d’identifier des cibles potentielles pour des stratégies populationnelles de prévention, les liens entre les caractéristiques du voisinage, l’obésité chez les jeunes et les habitudes de vie font de plus en plus l’objet d’études. Cependant, la recherche à ce jour comporte plusieurs incohérences. But: L’objectif général de cette thèse est d’étudier la contribution de différentes caractéristiques du voisinage relativement à l’obésité chez les jeunes et les habitudes de vie qui y sont associées. Les objectifs spécifiques consistent à: 1) Examiner les associations entre la présence de différents commerces d’alimentation dans les voisinages résidentiels et scolaires des enfants et leurs habitudes alimentaires; 2) Examiner comment l’exposition à certaines caractéristiques du voisinage résidentiel détermine l’obésité au niveau familial (chez le jeune, la mère et le père), ainsi que l’obésité individuelle pour chaque membre de la famille; 3) Identifier des combinaisons de facteurs de risque individuels, familiaux et du voisinage résidentiel qui prédisent le mieux l’obésité chez les jeunes, et déterminer si ces profils de facteurs de risque prédisent aussi un changement dans l’obésité après un suivi de deux ans. Méthodes: Les données proviennent de l’étude QUALITY, une cohorte québécoise de 630 jeunes, âgés de 8-10 ans au temps 1, avec une histoire d’obésité parentale. Les voisinages de 512 participants habitant la Région métropolitaine de Montréal ont été caractérisés à l’aide de : 1) données spatiales provenant du recensement et de bases de données administratives, calculées pour des zones tampons à partir du réseau routier et centrées sur le lieu de la résidence et de l’école; et 2) des observations menées par des évaluateurs dans le voisinage résidentiel. Les mesures du voisinage étudiées se rapportent aux caractéristiques de l’environnement bâti, social et alimentaire. L’obésité a été estimée aux temps 1 et 2 à l’aide de l’indice de masse corporelle (IMC) calculé à partir du poids et de la taille mesurés. Les habitudes alimentaires ont été mesurées au temps 1 à l'aide de trois rappels alimentaires. Les analyses effectuées comprennent, entres autres, des équations d'estimation généralisées, des régressions multiniveaux et des analyses prédictives basées sur des arbres de décision. Résultats: Les résultats démontrent la présence d’associations avec l’obésité chez les jeunes et les habitudes alimentaires pour certaines caractéristiques du voisinage. En particulier, la présence de dépanneurs et de restaurants-minutes dans le voisinage résidentiel et scolaire est associée avec de moins bonnes habitudes alimentaires. La présence accrue de trafic routier, ainsi qu’un faible niveau de prestige et d’urbanisation dans le voisinage résidentiel sont associés à l’obésité familiale. Enfin, les résultats montrent qu’habiter un voisinage obésogène, caractérisé par une défavorisation socioéconomique, la présence de moins de parcs et de plus de dépanneurs, prédit l'obésité chez les jeunes lorsque combiné à la présence de facteurs de risque individuels et familiaux. Conclusion: Cette thèse contribue aux écrits sur les voisinages et l’obésité chez les jeunes en considérant à la fois l'influence potentielle du voisinage résidentiel et scolaire ainsi que l’influence de l’environnement familial, en utilisant des méthodes objectives pour caractériser le voisinage et en utilisant des méthodes statistiques novatrices. Les résultats appuient en outre la notion que les efforts de prévention de l'obésité doivent cibler les multiples facteurs de risque de l'obésité chez les jeunes dans les environnements bâtis, sociaux et familiaux de ces jeunes.

Statistical Machine Learning Techniques for the Prediction of Learning Disabilities in School-Age Children

Learning Disability (LD) is a general term that describes specific kinds of learning problems. It is a neurological condition that affects a child's brain and impairs his ability to carry out one or many specific tasks. The learning disabled children are neither slow nor mentally retarded. This disorder can make it problematic for a child to learn as quickly or in the same way as some child who isn't affected by a learning disability. An affected child can have normal or above average intelligence. They may have difficulty paying attention, with reading or letter recognition, or with mathematics. It does not mean that children who have learning disabilities are less intelligent. In fact, many children who have learning disabilities are more intelligent than an average child. Learning disabilities vary from child to child. One child with LD may not have the same kind of learning problems as another child with LD. There is no cure for learning disabilities and they are life-long. However, children with LD can be high achievers and can be taught ways to get around the learning disability. In this research work, data mining using machine learning techniques are used to analyze the symptoms of LD, establish interrelationships between them and evaluate the relative importance of these symptoms. To increase the diagnostic accuracy of learning disability prediction, a knowledge based tool based on statistical machine learning or data mining techniques, with high accuracy,according to the knowledge obtained from the clinical information, is proposed. The basic idea of the developed knowledge based tool is to increase the accuracy of the learning disability assessment and reduce the time used for the same. Different statistical machine learning techniques in data mining are used in the study. Identifying the important parameters of LD prediction using the data mining techniques, identifying the hidden relationship between the symptoms of LD and estimating the relative significance of each symptoms of LD are also the parts of the objectives of this research work. The developed tool has many advantages compared to the traditional methods of using check lists in determination of learning disabilities. For improving the performance of various classifiers, we developed some preprocessing methods for the LD prediction system. A new system based on fuzzy and rough set models are also developed for LD prediction. Here also the importance of pre-processing is studied. A Graphical User Interface (GUI) is designed for developing an integrated knowledge based tool for prediction of LD as well as its degree. The designed tool stores the details of the children in the student database and retrieves their LD report as and when required. The present study undoubtedly proves the effectiveness of the tool developed based on various machine learning techniques. It also identifies the important parameters of LD and accurately predicts the learning disability in school age children. This thesis makes several major contributions in technical, general and social areas. The results are found very beneficial to the parents, teachers and the institutions. They are able to diagnose the child’s problem at an early stage and can go for the proper treatments/counseling at the correct time so as to avoid the academic and social losses.

‘Reliability Concepts in Quantile-based Analysis of Lifetime Data

Reliability analysis is a well established branch of statistics that deals with the statistical study of different aspects of lifetimes of a system of components. As we pointed out earlier that major part of the theory and applications in connection with reliability analysis were discussed based on the measures in terms of distribution function. In the beginning chapters of the thesis, we have described some attractive features of quantile functions and the relevance of its use in reliability analysis. Motivated by the works of Parzen (1979), Freimer et al. (1988) and Gilchrist (2000), who indicated the scope of quantile functions in reliability analysis and as a follow up of the systematic study in this connection by Nair and Sankaran (2009), in the present work we tried to extend their ideas to develop necessary theoretical framework for lifetime data analysis. In Chapter 1, we have given the relevance and scope of the study and a brief outline of the work we have carried out. Chapter 2 of this thesis is devoted to the presentation of various concepts and their brief reviews, which were useful for the discussions in the subsequent chapters .In the introduction of Chapter 4, we have pointed out the role of ageing concepts in reliability analysis and in identifying life distributions .In Chapter 6, we have studied the first two L-moments of residual life and their relevance in various applications of reliability analysis. We have shown that the first L-moment of residual function is equivalent to the vitality function, which have been widely discussed in the literature .In Chapter 7, we have defined percentile residual life in reversed time (RPRL) and derived its relationship with reversed hazard rate (RHR). We have discussed the characterization problem of RPRL and demonstrated with an example that the RPRL for given does not determine the distribution uniquely

"Statistical Methods in Gear Selectivity and Gear Efficiency Studies”

The preceding discussion and review of literature show that studies on gear selectivity have received great attention, while gear efficiency studies do not seem to have received equal consideration. In temperate waters, fishing industry is well organised and relatively large and well equipped vessels and gear are used for commercial fishing and the number of species are less; whereas in tropics particularly in India, small scale fishery dominates the scene and the fishery is multispecies operated upon by nmltigear. Therefore many of the problems faced in India may not exist in developed countries. Perhaps this would be the reason for the paucity of literature on the problems in estimation of relative efficiency. Much work has been carried out in estimating relative efficiency (Pycha, 1962; Pope, 1963; Gulland, 1967; Dickson, 1971 and Collins, 1979). The main subject of interest in the present thesis is an investigation into the problems in the comparison of fishing gears. especially in using classical test procedures with special reference to the prevailing fishing practices (that is. with reference to the catch data generated by the existing system). This has been taken up with a view to standardizing an approach for comparing the efficiency of fishing gear. Besides this, the implications of the terms ‘gear efficiency‘ and ‘gear selectivity‘ have been examined and based on the commonly used selectivity model (Holt, 1963), estimation of the ratio of fishing power of two gear has been considered. An attempt to determine the size of fish for which a gear is most efficient.has also been made. The work has been presented in eight chapters

Spectral and statistical characteristics of shoaling waves of Alleppey West coast of India

Some investigations on the spectral and statistical characteristics of deep water waves are available for Indian waters. But practically no systematic investigation on the shallow water wave spectral and probabilistic characteristics is made for any part of the Indian coast except for a few restricted studies. Hence a comprehensive study of the shallow water wave climate and their spectral and statistical characteristics for a location (Alleppey) along the southwest coast of India is undertaken based on recorded data. The results of the investigation are presented in this thesis.The thesis comprises of seven chapters

Comparison of Statistical and Semantic Similarity Techniques for Paraphrase Identification

This paper compares statistical technique of paraphrase identification to semantic technique of paraphrase identification. The statistical techniques used for comparison are word set and word-order based methods where as the semantic technique used is the WordNet similarity matrix method described by Stevenson and Fernando in [3].

ECG Noise Removal using GA tuned Sign-Data Least Mean Square Algorithm

Adaptive filter is a primary method to filter Electrocardiogram (ECG), because it does not need the signal statistical characteristics. In this paper, an adaptive filtering technique for denoising the ECG based on Genetic Algorithm (GA) tuned Sign-Data Least Mean Square (SD-LMS) algorithm is proposed. This technique minimizes the mean-squared error between the primary input, which is a noisy ECG, and a reference input which can be either noise that is correlated in some way with the noise in the primary input or a signal that is correlated only with ECG in the primary input. Noise is used as the reference signal in this work. The algorithm was applied to the records from the MIT -BIH Arrhythmia database for removing the baseline wander and 60Hz power line interference. The proposed algorithm gave an average signal to noise ratio improvement of 10.75 dB for baseline wander and 24.26 dB for power line interference which is better than the previous reported works

Development of Hierarchical Clustering Techniques for Gridded Data from Mixed Data Sequences

Knowledge discovery in databases is the non-trivial process of identifying valid, novel potentially useful and ultimately understandable patterns from data. The term Data mining refers to the process which does the exploratory analysis on the data and builds some model on the data. To infer patterns from data, data mining involves different approaches like association rule mining, classification techniques or clustering techniques. Among the many data mining techniques, clustering plays a major role, since it helps to group the related data for assessing properties and drawing conclusions. Most of the clustering algorithms act on a dataset with uniform format, since the similarity or dissimilarity between the data points is a significant factor in finding out the clusters. If a dataset consists of mixed attributes, i.e. a combination of numerical and categorical variables, a preferred approach is to convert different formats into a uniform format. The research study explores the various techniques to convert the mixed data sets to a numerical equivalent, so as to make it equipped for applying the statistical and similar algorithms. The results of clustering mixed category data after conversion to numeric data type have been demonstrated using a crime data set. The thesis also proposes an extension to the well known algorithm for handling mixed data types, to deal with data sets having only categorical data. The proposed conversion has been validated on a data set corresponding to breast cancer. Moreover, another issue with the clustering process is the visualization of output. Different geometric techniques like scatter plot, or projection plots are available, but none of the techniques display the result projecting the whole database but rather demonstrate attribute-pair wise analysis

Parameter identification of structural dynamic models by inverse statistical analysis

Auf dem Gebiet der Strukturdynamik sind computergestützte Modellvalidierungstechniken inzwischen weit verbreitet. Dabei werden experimentelle Modaldaten, um ein numerisches Modell für weitere Analysen zu korrigieren. Gleichwohl repräsentiert das validierte Modell nur das dynamische Verhalten der getesteten Struktur. In der Realität gibt es wiederum viele Faktoren, die zwangsläufig zu variierenden Ergebnissen von Modaltests führen werden: Sich verändernde Umgebungsbedingungen während eines Tests, leicht unterschiedliche Testaufbauten, ein Test an einer nominell gleichen aber anderen Struktur (z.B. aus der Serienfertigung), etc. Damit eine stochastische Simulation durchgeführt werden kann, muss eine Reihe von Annahmen für die verwendeten Zufallsvariablengetroffen werden. Folglich bedarf es einer inversen Methode, die es ermöglicht ein stochastisches Modell aus experimentellen Modaldaten zu identifizieren. Die Arbeit beschreibt die Entwicklung eines parameter-basierten Ansatzes, um stochastische Simulationsmodelle auf dem Gebiet der Strukturdynamik zu identifizieren. Die entwickelte Methode beruht auf Sensitivitäten erster Ordnung, mit denen Parametermittelwerte und Kovarianzen des numerischen Modells aus stochastischen experimentellen Modaldaten bestimmt werden können.

A Statistical Image-Based Shape Model for Visual Hull Reconstruction and 3D Structure Inference

We present a statistical image-based shape + structure model for Bayesian visual hull reconstruction and 3D structure inference. The 3D shape of a class of objects is represented by sets of contours from silhouette views simultaneously observed from multiple calibrated cameras. Bayesian reconstructions of new shapes are then estimated using a prior density constructed with a mixture model and probabilistic principal components analysis. We show how the use of a class-specific prior in a visual hull reconstruction can reduce the effect of segmentation errors from the silhouette extraction process. The proposed method is applied to a data set of pedestrian images, and improvements in the approximate 3D models under various noise conditions are shown. We further augment the shape model to incorporate structural features of interest; unknown structural parameters for a novel set of contours are then inferred via the Bayesian reconstruction process. Model matching and parameter inference are done entirely in the image domain and require no explicit 3D construction. Our shape model enables accurate estimation of structure despite segmentation errors or missing views in the input silhouettes, and works even with only a single input view. Using a data set of thousands of pedestrian images generated from a synthetic model, we can accurately infer the 3D locations of 19 joints on the body based on observed silhouette contours from real images.

Active Learning with Statistical Models

For many types of learners one can compute the statistically 'optimal' way to select data. We review how these techniques have been used with feedforward neural networks. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

Learning from Incomplete Data

Real-world learning tasks often involve high-dimensional data sets with complex patterns of missing features. In this paper we review the problem of learning from incomplete data from two statistical perspectives---the likelihood-based and the Bayesian. The goal is two-fold: to place current neural network approaches to missing data within a statistical framework, and to describe a set of algorithms, derived from the likelihood-based framework, that handle clustering, classification, and function approximation from incomplete data in a principled and efficient manner. These algorithms are based on mixture modeling and make two distinct appeals to the Expectation-Maximization (EM) principle (Dempster, Laird, and Rubin 1977)---both for the estimation of mixture components and for coping with the missing data.

Possible solution of some essential zero problems in compositional data analysis

One of the tantalising remaining problems in compositional data analysis lies in how to deal with data sets in which there are components which are essential zeros. By an essential zero we mean a component which is truly zero, not something recorded as zero simply because the experimental design or the measuring instrument has not been sufficiently sensitive to detect a trace of the part. Such essential zeros occur in many compositional situations, such as household budget patterns, time budgets, palaeontological zonation studies, ecological abundance studies. Devices such as nonzero replacement and amalgamation are almost invariably ad hoc and unsuccessful in such situations. From consideration of such examples it seems sensible to build up a model in two stages, the first determining where the zeros will occur and the second how the unit available is distributed among the non-zero parts. In this paper we suggest two such models, an independent binomial conditional logistic normal model and a hierarchical dependent binomial conditional logistic normal model. The compositional data in such modelling consist of an incidence matrix and a conditional compositional matrix. Interesting statistical problems arise, such as the question of estimability of parameters, the nature of the computational process for the estimation of both the incidence and compositional parameters caused by the complexity of the subcompositional structure, the formation of meaningful hypotheses, and the devising of suitable testing methodology within a lattice of such essential zero-compositional hypotheses. The methodology is illustrated by application to both simulated and real compositional data