Causal loops and the independence of causal facts

According to Hugh Mellor in Real Time II (1998, Ch. 12), assuming the logical independence of causal facts and the 'law of large numbers', causal loops are impossible because if they were possible they would produce inconsistent sets of frequencies. I clarify the argument, and argue that it would be preferable to abandon the relevant independence assumption in the case of causal loops.

Dual processes in recognition: Does a focus on measurement operations provide a sufficient foundation?

Current theoretical thinking about dual processes in recognition relies heavily on the measurement operations embodied within the process dissociation procedure. We critically evaluate the ability of this procedure to support this theoretical enterprise. We show that there are alternative processes that would produce a rough invariance in familiarity (a key prediction of the dual-processing approach) and that the process dissociation procedure does not have the power to differentiate between these alternative possibilities. We also show that attempts to relate parameters estimated by the process dissociation procedure to subjective reports (remember-know judgments) cannot differentiate between alternative dual-processing models and that there are problems with some of the historical evidence and with obtaining converging evidence. Our conclusion is that more specific theories incorporating ideas about representation and process are required.

A priori ratemaking using bivariate poisson regression models

In automobile insurance, it is useful to achieve a priori ratemaking by resorting to gene- ralized linear models, and here the Poisson regression model constitutes the most widely accepted basis. However, insurance companies distinguish between claims with or without bodily injuries, or claims with full or partial liability of the insured driver. This paper exa- mines an a priori ratemaking procedure when including two di®erent types of claim. When assuming independence between claim types, the premium can be obtained by summing the premiums for each type of guarantee and is dependent on the rating factors chosen. If the independence assumption is relaxed, then it is unclear as to how the tari® system might be a®ected. In order to answer this question, bivariate Poisson regression models, suitable for paired count data exhibiting correlation, are introduced. It is shown that the usual independence assumption is unrealistic here. These models are applied to an automobile insurance claims database containing 80,994 contracts belonging to a Spanish insurance company. Finally, the consequences for pure and loaded premiums when the independence assumption is relaxed by using a bivariate Poisson regression model are analysed.

Modelling dependence in a ratemaking procedure with multivariate Poisson regression models

When actuaries face with the problem of pricing an insurance contract that contains different types of coverage, such as a motor insurance or homeowner's insurance policy, they usually assume that types of claim are independent. However, this assumption may not be realistic: several studies have shown that there is a positive correlation between types of claim. Here we introduce different regression models in order to relax the independence assumption, including zero-inflated models to account for excess of zeros and overdispersion. These models have been largely ignored to multivariate Poisson date, mainly because of their computational di±culties. Bayesian inference based on MCMC helps to solve this problem (and also lets us derive, for several quantities of interest, posterior summaries to account for uncertainty). Finally, these models are applied to an automobile insurance claims database with three different types of claims. We analyse the consequences for pure and loaded premiums when the independence assumption is relaxed by using different multivariate Poisson regression models and their zero-inflated versions.

Problems of the randomization test for AB designs

N = 1 designs imply repeated registrations of the behaviour of the same experimental unit and the measurements obtained are often few due to time limitations, while they are also likely to be sequentially dependent. The analytical techniques needed to enhance statistical and clinical decision making have to deal with these problems. Different procedures for analysing data from single-case AB designs are discussed, presenting their main features and revising the results reported by previous studies. Randomization tests represent one of the statistical methods that seemed to perform well in terms of controlling false alarm rates. In the experimental part of the study a new simulation approach is used to test the performance of randomization tests and the results suggest that the technique is not always robust against the violation of the independence assumption. Moreover, sensitivity proved to be generally unacceptably low for series lengths equal to 30 and 40. Considering the evidence available, there does not seem to be an optimal technique for single-case data analysis

Modèle de mélange de lois multinormales appliqué à l'analyse de comportements et d'habiletés cognitives d'enfants.

Cette étude aborde le thème de l’utilisation des modèles de mélange de lois pour analyser des données de comportements et d’habiletés cognitives mesurées à plusieurs moments au cours du développement des enfants. L’estimation des mélanges de lois multinormales en utilisant l’algorithme EM est expliquée en détail. Cet algorithme simplifie beaucoup les calculs, car il permet d’estimer les paramètres de chaque groupe séparément, permettant ainsi de modéliser plus facilement la covariance des observations à travers le temps. Ce dernier point est souvent mis de côté dans les analyses de mélanges. Cette étude porte sur les conséquences d’une mauvaise spécification de la covariance sur l’estimation du nombre de groupes formant un mélange. La conséquence principale est la surestimation du nombre de groupes, c’est-à-dire qu’on estime des groupes qui n’existent pas. En particulier, l’hypothèse d’indépendance des observations à travers le temps lorsque ces dernières étaient corrélées résultait en l’estimation de plusieurs groupes qui n’existaient pas. Cette surestimation du nombre de groupes entraîne aussi une surparamétrisation, c’est-à-dire qu’on utilise plus de paramètres qu’il n’est nécessaire pour modéliser les données. Finalement, des modèles de mélanges ont été estimés sur des données de comportements et d’habiletés cognitives. Nous avons estimé les mélanges en supposant d’abord une structure de covariance puis l’indépendance. On se rend compte que dans la plupart des cas l’ajout d’une structure de covariance a pour conséquence d’estimer moins de groupes et les résultats sont plus simples et plus clairs à interpréter.

Geometric Aspects of Visual Object Recognition

This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.

Adding one risk to another: generalizing the unavoidable (background) risk

This paper provides a complete generalization of the background risk models. In so doing, first, it relaxes the independence assumption. Second, it adopts a general functional form. Third, itadopts a general type of risk. Furthermore, it introduces a new general form of background risk.

Planejamento experimental aplicada a um novo separador líquido-líquido utilizado no tratamento de águas residuais contaminadas com petróleo

The present work had as objective to apply an experimental planning aiming at to improve the efficiency of separation of a new type of mixer-settler applied to treat waste water contaminated with oil. An unity in scale of laboratory, was installed in the Post-graduation Program of Chemical Engineering of UFRN. It was constructed in partnership with Petrobras S.A. This called device Misturador-Decantador a Inversão de Fases (MDIF) , possess features of conventional mixer-settler and spray column type. The equipment is composed of three main parts: mixing chamber; chamber of decantation and chamber of separation. The efficiency of separation is evaluated analyzing the oil concentrations in water in the feed and the output of the device. For the analysis one used the gravimetric method of oil and greases analysis (TOG). The system in study is a water of formation emulsified with oil. The used extractant is a mixture of Turpentine spirit hydro-carbons, supplied for Petrobras. It was applied, for otimization of the efficiency of separation of the equipment, an experimental planning of the composite central type, having as factorial portion fractionary factorial planning 2 5-2, with the magnifying of the type star and five replications in the central point. In this work, the following independents variables were studied: contents of oil in the feed of the device; volumetric ratio (O/A); total flowrate ; agitation in the mixing chamber and height of the organic bed. Minimum and maximum limits for the studied variables had been fixed according previous works. The analysis of variance for the equation of the empirical model, revealed statistically significant and useful results for predictions ends. The variance analysis also presented the distribution of the error as a normal distribution and was observed that as the dispersions do not depend on the levels of the factors, the independence assumption can be verified. The variation around the average is explained by 98.98%, or either, equal to the maximum value, being the smoothing of the model in relation to the experimental points of 0,98981. The results present a strong interaction between the variable oil contents in the feed and agitation in the mixing chamber, having great and positive influence in the separation efficiency. Another variable that presented a great positive influence was the height of the organic bed. The best results of separation efficiency had been obtained for high flowrates when associates the high oil concentrations and high agitation. The results of the present work had shown excellent agreement with the results carried out through previous works with the mixer-settler of phase inversion

Gráfico de Hotelling com esquemas especiais de amostragem para o monitoramento de processos bivariados autocorrelacionados

Pós-graduação em Engenharia Mecânica - FEG

Class-Conditional Probabilistic Principal Component Analysis: application to gender recognition

Este trabajo presenta una solución al problema del reconocimiento del género de un rostro humano a partir de una imagen. Adoptamos una aproximación que utiliza la cara completa a través de la textura de la cara normalizada y redimensionada como entrada a un clasificador Näive Bayes. Presentamos la técnica de Análisis de Componentes Principales Probabilístico Condicionado-a-la-Clase (CC-PPCA) para reducir la dimensionalidad de los vectores de características para la clasificación y asegurar la asunción de independencia para el clasificador. Esta nueva aproximación tiene la deseable propiedad de presentar un modelo paramétrico sencillo para las marginales. Además, este modelo puede estimarse con muy pocos datos. En los experimentos que hemos desarrollados mostramos que CC-PPCA obtiene un 90% de acierto en la clasificación, resultado muy similar al mejor presentado en la literatura---ABSTRACT---This paper presents a solution to the problem of recognizing the gender of a human face from an image. We adopt a holistic approach by using the cropped and normalized texture of the face as input to a Naïve Bayes classifier. First it is introduced the Class-Conditional Probabilistic Principal Component Analysis (CC-PPCA) technique to reduce the dimensionality of the classification attribute vector and enforce the independence assumption of the classifier. This new approach has the desirable property of a simple parametric model for the marginals. Moreover this model can be estimated with very few data. In the experiments conducted we show that using CCPPCA we get 90% classification accuracy, which is similar result to the best in the literature. The proposed method is very simple to train and implement.

The v-MFG test: Investigating maternal, offspring and maternal-fetal genetic incompatibility effects on disease and viability

The MFG test is a family-based association test that detects genetic effects contributing to disease in offspring, including offspring allelic effects, maternal allelic effects and MFG incompatibility effects. Like many other family-based association tests, it assumes that the offspring survival and the offspring-parent genotypes are conditionally independent provided the offspring is affected. However, when the putative disease-increasing locus can affect another competing phenotype, for example, offspring viability, the conditional independence assumption fails and these tests could lead to incorrect conclusions regarding the role of the gene in disease. We propose the v-MFG test to adjust for the genetic effects on one phenotype, e.g., viability, when testing the effects of that locus on another phenotype, e.g., disease. Using genotype data from nuclear families containing parents and at least one affected offspring, the v-MFG test models the distribution of family genotypes conditional on offspring phenotypes. It simultaneously estimates genetic effects on two phenotypes, viability and disease. Simulations show that the v-MFG test produces accurate genetic effect estimates on disease as well as on viability under several different scenarios. It generates accurate type-I error rates and provides adequate power with moderate sample sizes to detect genetic effects on disease risk when viability is reduced. We demonstrate the v-MFG test with HLA-DRB1 data from study participants with rheumatoid arthritis (RA) and their parents, we show that the v-MFG test successfully detects an MFG incompatibility effect on RA while simultaneously adjusting for a possible viability loss.

Estimation du paramètre d'une copule archimedienne en présence de censure dépendante

Les méthodes classiques d’analyse de survie notamment la méthode non paramétrique de Kaplan et Meier (1958) supposent l’indépendance entre les variables d’intérêt et de censure. Mais, cette hypothèse d’indépendance n’étant pas toujours soutenable, plusieurs auteurs ont élaboré des méthodes pour prendre en compte la dépendance. La plupart de ces méthodes émettent des hypothèses sur cette dépendance. Dans ce mémoire, nous avons proposé une méthode d’estimation de la dépendance en présence de censure dépendante qui utilise le copula-graphic estimator pour les copules archimédiennes (Rivest etWells, 2001) et suppose la connaissance de la distribution de la variable de censure. Nous avons ensuite étudié la consistance de cet estimateur à travers des simulations avant de l’appliquer sur un jeu de données réelles.