An analysis of the spatiotemporal distribution of American cutaneous leishmaniasis in counties located along road and railway corridors in the State of Maranhao, Brazil

Introduction The incidence of American cutaneous leishmaniasis (ACL) is increasing in Latin America, especially in Brazil, where 256,587 cases were confirmed in the last decade. Methods This study used a Bayesian model to examine the spatial and temporal distribution of ACL cases between 2000 and 2009 in 61 counties of State of Maranhão located along the three main road and railway corridors. Results During the study period, 13,818 cases of ACL were recorded. There was a significant decrease in the incidence of ACL in the ten study years. The recorded incidence rate ranged from 7.36 to 241.45 per 100,000 inhabitants. The relative risk increased in 77% of the counties, decreased in 18% and was maintained in only five counties. Conclusions Although there was a decreased incidence of the disease, ACL was present in all of the examined municipalities, thus maintaining the risk of contracting this illness.

A New Index of Financial Conditions

We use factor augmented vector autoregressive models with time-varying coefficients to construct a financial conditions index. The time-variation in the parameters allows for the weights attached to each financial variable in the index to evolve over time. Furthermore, we develop methods for dynamic model averaging or selection which allow the financial variables entering into the FCI to change over time. We discuss why such extensions of the existing literature are important and show them to be so in an empirical application involving a wide range of financial variables.

Prior selection for panel vector autoregressions

There is a vast literature that specifies Bayesian shrinkage priors for vector autoregressions (VARs) of possibly large dimensions. In this paper I argue that many of these priors are not appropriate for multi-country settings, which motivates me to develop priors for panel VARs (PVARs). The parametric and semi-parametric priors I suggest not only perform valuable shrinkage in large dimensions, but also allow for soft clustering of variables or countries which are homogeneous. I discuss the implications of these new priors for modelling interdependencies and heterogeneities among different countries in a panel VAR setting. Monte Carlo evidence and an empirical forecasting exercise show clear and important gains of the new priors compared to existing popular priors for VARs and PVARs.

Area deprivation and mortality in the provincial capital cities of Andalusia and Catalonia (Spain)

Objective: To study the linkage between material deprivation and mortality from all causes, for men and women separately, in the capital cities of the provinces in Andalusia and Catalonia (Spain). Methods: A small-area ecological study was devised using the census section as the unit for analysis. 188 983 Deaths occurring in the capital cities of the Andalusian provinces and 109 478 deaths recorded in the Catalan capital cities were examined. Principal components factorial analysis was used to devise a material deprivation index comprising the percentage of manual labourers, unemployment and illiteracy. A hierarchical Bayesian model was used to study the relationship between mortality and area deprivation. Main results: In most cities, results show an increased male mortality risk in the most deprived areas in relation to the least depressed. In Andalusia, the relative risks between the highest and lowest deprivation decile ranged from 1.24 (Malaga) to 1.40 (Granada), with 95% credibility intervals showing a significant excess risk. In Catalonia, relative risks ranged between 1.08 (Girona) and 1.50 (Tarragona). No evidence was found for an excess of female mortality in most deprived areas in either of the autonomous communities. Conclusions: Within cities, gender-related differences were revealed when deprivation was correlated geographically with mortality rates. These differences were found from an ecological perspective. Further research is needed in order to validate these results from an individual approach. The idea to be analysed is to identify those factors that explain these differences at an individual level.

Confounding factors and genetic polymorphism in the evaluation of individual steroid profiling

In the fight against doping, steroid profiling is a powerful tool to detect drug misuse with endogenous anabolic androgenic steroids. To establish sensitive and reliable models, the factors influencing profiling should be recognised. We performed an extensive literature review of the multiple factors that could influence the quantitative levels and ratios of endogenous steroids in urine matrix. For a comprehensive and scientific evaluation of the urinary steroid profile, it is necessary to define the target analytes as well as testosterone metabolism. The two main confounding factors, that is, endogenous and exogenous factors, are detailed to show the complex process of quantifying the steroid profile within WADA-accredited laboratories. Technical aspects are also discussed as they could have a significant impact on the steroid profile, and thus the steroid module of the athlete biological passport (ABP). The different factors impacting the major components of the steroid profile must be understood to ensure scientifically sound interpretation through the Bayesian model of the ABP. Not only should the statistical data be considered but also the experts in the field must be consulted for successful implementation of the steroidal module.

Processus de reconnaissance et d'identification de personnes décédées

Recognition and identification processes for deceased persons. Determining the identity of deceased persons is a routine task performed essentially by police departments and forensic experts. This thesis highlights the processes necessary for the proper and transparent determination of the civil identities of deceased persons. The identity of a person is defined as the establishment of a link between that person ("the source") and information pertaining to the same individual ("identifiers"). Various identity forms could emerge, depending on the nature of the identifiers. There are two distinct types of identity, namely civil identity and biological identity. The paper examines four processes: identification by witnesses (the recognition process) and comparisons of fingerprints, dental data and DNA profiles (the identification processes). During the recognition process, the memory function is examined and helps to clarify circumstances that may give rise to errors. To make the process more rigorous, a body presentation procedure is proposed to investigators. Before examining the other processes, three general concepts specific to forensic science are considered with regard to the identification of a deceased person, namely, matter divisibility (Inman and Rudin), transfer (Locard) and uniqueness (Kirk). These concepts can be applied to the task at hand, although some require a slightly broader scope of application. A cross comparison of common forensic fields and the identification of deceased persons reveals certain differences, including 1 - reverse positioning of the source (i.e. the source is not sought from traces, but rather the identifiers are obtained from the source); 2 - the need for civil identity determination in addition to the individualisation stage; and 3 - a more restricted population (closed set), rather than an open one. For fingerprints, dental and DNA data, intravariability and intervariability are examined, as well as changes in these post mortem (PM) identifiers. Ante-mortem identifiers (AM) are located and AM-PM comparisons made. For DNA, it has been shown that direct identifiers (taken from a person whose civil identity has been alleged) tend to lead to determining civil identity whereas indirect identifiers (obtained from a close relative) direct towards a determination of biological identity. For each process, a Bayesian model is presented which includes sources of uncertainty deemed to be relevant. The results of the different processes combine to structure and summarise an overall outcome and a methodology. The modelling of dental data presents a specific difficulty with respect to intravariability, which in itself is not quantifiable. The concept of "validity" is, therefore, suggested as a possible solution to the problem. Validity uses various parameters that have an acknowledged impact on teeth intravariability. In cases where identifying deceased persons proves to be extremely difficult due to the limited discrimination of certain procedures, the use of a Bayesian approach is of great value in bringing a transparent and synthetic value. RESUME : Titre: Processus de reconnaissance et d'identification de personnes décédées. L'individualisation de personnes décédées est une tâche courante partagée principalement par des services de police, des odontologues et des laboratoires de génétique. L'objectif de cette recherche est de présenter des processus pour déterminer valablement, avec une incertitude maîtrisée, les identités civiles de personnes décédées. La notion d'identité est examinée en premier lieu. L'identité d'une personne est définie comme l'établissement d'un lien entre cette personne et des informations la concernant. Les informations en question sont désignées par le terme d'identifiants. Deux formes distinctes d'identité sont retenues: l'identité civile et l'identité biologique. Quatre processus principaux sont examinés: celui du témoignage et ceux impliquant les comparaisons d'empreintes digitales, de données dentaires et de profils d'ADN. Concernant le processus de reconnaissance, le mode de fonctionnement de la mémoire est examiné, démarche qui permet de désigner les paramètres pouvant conduire à des erreurs. Dans le but d'apporter un cadre rigoureux à ce processus, une procédure de présentation d'un corps est proposée à l'intention des enquêteurs. Avant d'entreprendre l'examen des autres processus, les concepts généraux propres aux domaines forensiques sont examinés sous l'angle particulier de l'identification de personnes décédées: la divisibilité de la matière (Inman et Rudin), le transfert (Locard) et l'unicité (Kirk). Il est constaté que ces concepts peuvent être appliqués, certains nécessitant toutefois un léger élargissement de leurs principes. Une comparaison croisée entre les domaines forensiques habituels et l'identification de personnes décédées montre des différences telles qu'un positionnement inversé de la source (la source n'est plus à rechercher en partant de traces, mais ce sont des identifiants qui sont recherchés en partant de la source), la nécessité de devoir déterminer une identité civile en plus de procéder à une individualisation ou encore une population d'intérêt limitée plutôt qu'ouverte. Pour les empreintes digitales, les dents et l'ADN, l'intra puis l'inter-variabilité sont examinées, de même que leurs modifications post-mortem (PM), la localisation des identifiants ante-mortem (AM) et les comparaisons AM-PM. Pour l'ADN, il est démontré que les identifiants directs (provenant de la personne dont l'identité civile est supposée) tendent à déterminer une identité civile alors que les identifiants indirects (provenant d'un proche parent) tendent à déterminer une identité biologique. Puis une synthèse des résultats provenant des différents processus est réalisée grâce à des modélisations bayesiennes. Pour chaque processus, une modélisation est présentée, modélisation intégrant les paramètres reconnus comme pertinents. À ce stade, une difficulté apparaît: celle de quantifier l'intra-variabilité dentaire pour laquelle il n'existe pas de règle précise. La solution préconisée est celle d'intégrer un concept de validité qui intègre divers paramètres ayant un impact connu sur l'intra-variabilité. La possibilité de formuler une valeur de synthèse par l'approche bayesienne s'avère d'une aide précieuse dans des cas très difficiles pour lesquels chacun des processus est limité en termes de potentiel discriminant.

Residence time, expansion toward the equator in the invaded range and native range size matter to climatic niche shifts in non-native species

Aim Identifying climatic niche shifts and their drivers is important to accurately predict the risk of biological invasions. The niches of non-native plants and birds have recently been assessed in large-scale multi-species studies, but such large-scale tests are lacking for non-native reptiles and amphibians (herpetofauna). Furthermore, little is known about the factors contributing to niche shifts when they occur. Based on the occurrence of 71 reptile and amphibian species, we compared native and non-native realized niches in 101 invaded ranges at a worldwide scale and identified the factors that affect niche shifts. Location The world except the Antarctic. Methods We assessed climatic niche dynamics in a gridded environmental space allowing the quantification of niche overlap and expansion into climatic conditions not colonized by the species in their native range. We analyzed the factors affecting niche shifts using a model averaging approach based on generalized linear mixed-effects models. Results Approximately 57% of the invaded ranges (51% for amphibians and 61% for reptiles) showed niche shifts (≥10% expansion in the realized climatic niche). Island endemics, species introduced to Oceania and invaded ranges outside the native biogeographic realm showed a higher proportion of niche shifts. Niche shifts were more likely for species that had smaller native range sizes, were introduced earlier into a new range or invaded areas located at lower latitudes than the native range. Main conclusions The proportion of niche shifts for non-native herpetofauna was higher than those for Holarctic non-native plants and European non-native birds. The 'climate matching hypothesis' should be used with caution for species shifting their niche because it could underestimate the risk of their establishment.

The effect of scale in daily precipitation hazard assessment

Daily precipitation is recorded as the total amount of water collected by a rain-gauge in 24 h. Events are modelled as a Poisson process and the 24 h precipitation by a Generalised Pareto Distribution (GPD) of excesses. Hazard assessment is complete when estimates of the Poisson rate and the distribution parameters, together with a measure of their uncertainty, are obtained. The shape parameter of the GPD determines the support of the variable: Weibull domain of attraction (DA) corresponds to finite support variables as should be for natural phenomena. However, Fréchet DA has been reported for daily precipitation, which implies an infinite support and a heavy-tailed distribution. Bayesian techniques are used to estimate the parameters. The approach is illustrated with precipitation data from the Eastern coast of the Iberian Peninsula affected by severe convective precipitation. The estimated GPD is mainly in the Fréchet DA, something incompatible with the common sense assumption of that precipitation is a bounded phenomenon. The bounded character of precipitation is then taken as a priori hypothesis. Consistency of this hypothesis with the data is checked in two cases: using the raw-data (in mm) and using log-transformed data. As expected, a Bayesian model checking clearly rejects the model in the raw-data case. However, log-transformed data seem to be consistent with the model. This fact may be due to the adequacy of the log-scale to represent positive measurements for which differences are better relative than absolute

Social differences in avoidable mortality between small areas of 15 European cities: an ecological study

Health and inequalities in health among inhabitants of European cities are of major importance for European public health and there is great interest in how different health care systems in Europe perform in the reduction of health inequalities. However, evidence on the spatial distribution of cause-specific mortality across neighbourhoods of European cities is scarce. This study presents maps of avoidable mortality in European cities and analyses differences in avoidable mortality between neighbourhoods with different levels of deprivation. Methods: We determined the level of mortality from 14 avoidable causes of death for each neighbourhood of 15 large cities in different European regions. To address the problems associated with Standardised Mortality Ratios for small areas we smooth them using the Bayesian model proposed by Besag, York and Mollié. Ecological regression analysis was used to assess the association between social deprivation and mortality. Results: Mortality from avoidable causes of death is higher in deprived neighbourhoods and mortality rate ratios between areas with different levels of deprivation differ between gender and cities. In most cases rate ratios are lower among women. While Eastern and Southern European cities show higher levels of avoidable mortality, the association of mortality with social deprivation tends to be higher in Northern and lower in Southern Europe. Conclusions: There are marked differences in the level of avoidable mortality between neighbourhoods of European cities and the level of avoidable mortality is associated with social deprivation. There is no systematic difference in the magnitude of this association between European cities or regions. Spatial patterns of avoidable mortality across small city areas can point to possible local problems and specific strategies to reduce health inequality which is important for the development of urban areas and the well-being of their inhabitants

Simulating the performance of paper machine control

The topic of this thesis is the simulation of a combination of several control and data assimilation methods, meant to be used for controlling the quality of paper in a paper machine. Paper making is a very complex process and the information obtained from the web is sparse. A paper web scanner can only measure a zig zag path on the web. An assimilation method is needed to process estimates for Machine Direction (MD) and Cross Direction (CD) profiles of the web. Quality control is based on these measurements. There is an increasing need for intelligent methods to assist in data assimilation. The target of this thesis is to study how such intelligent assimilation methods are affecting paper web quality. This work is based on a paper web simulator, which has been developed in the TEKES funded MASI NoTes project. The simulator is a valuable tool in comparing different assimilation methods. The thesis contains the comparison of four different assimilation methods. These data assimilation methods are a first order Bayesian model estimator, an ARMA model based on a higher order Bayesian estimator, a Fourier transform based Kalman filter estimator and a simple block estimator. The last one can be considered to be close to current operational methods. From these methods Bayesian, ARMA and Kalman all seem to have advantages over the commercial one. The Kalman and ARMA estimators seems to be best in overall performance.

Évaluation d'un modèle a priori basé sur un seuillage de la TCD en super-résolution et comparaison avec d'autres modèles a priori

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

Modélisation bayésienne des changements aux niches écologiques causés par le réchauffement climatique

Cette thèse présente des méthodes de traitement de données de comptage en particulier et des données discrètes en général. Il s'inscrit dans le cadre d'un projet stratégique du CRNSG, nommé CC-Bio, dont l'objectif est d'évaluer l'impact des changements climatiques sur la répartition des espèces animales et végétales. Après une brève introduction aux notions de biogéographie et aux modèles linéaires mixtes généralisés aux chapitres 1 et 2 respectivement, ma thèse s'articulera autour de trois idées majeures. Premièrement, nous introduisons au chapitre 3 une nouvelle forme de distribution dont les composantes ont pour distributions marginales des lois de Poisson ou des lois de Skellam. Cette nouvelle spécification permet d'incorporer de l'information pertinente sur la nature des corrélations entre toutes les composantes. De plus, nous présentons certaines propriétés de ladite distribution. Contrairement à la distribution multidimensionnelle de Poisson qu'elle généralise, celle-ci permet de traiter les variables avec des corrélations positives et/ou négatives. Une simulation permet d'illustrer les méthodes d'estimation dans le cas bidimensionnel. Les résultats obtenus par les méthodes bayésiennes par les chaînes de Markov par Monte Carlo (CMMC) indiquent un biais relatif assez faible de moins de 5% pour les coefficients de régression des moyennes contrairement à ceux du terme de covariance qui semblent un peu plus volatils. Deuxièmement, le chapitre 4 présente une extension de la régression multidimensionnelle de Poisson avec des effets aléatoires ayant une densité gamma. En effet, conscients du fait que les données d'abondance des espèces présentent une forte dispersion, ce qui rendrait fallacieux les estimateurs et écarts types obtenus, nous privilégions une approche basée sur l'intégration par Monte Carlo grâce à l'échantillonnage préférentiel. L'approche demeure la même qu'au chapitre précédent, c'est-à-dire que l'idée est de simuler des variables latentes indépendantes et de se retrouver dans le cadre d'un modèle linéaire mixte généralisé (GLMM) conventionnel avec des effets aléatoires de densité gamma. Même si l'hypothèse d'une connaissance a priori des paramètres de dispersion semble trop forte, une analyse de sensibilité basée sur la qualité de l'ajustement permet de démontrer la robustesse de notre méthode. Troisièmement, dans le dernier chapitre, nous nous intéressons à la définition et à la construction d'une mesure de concordance donc de corrélation pour les données augmentées en zéro par la modélisation de copules gaussiennes. Contrairement au tau de Kendall dont les valeurs se situent dans un intervalle dont les bornes varient selon la fréquence d'observations d'égalité entre les paires, cette mesure a pour avantage de prendre ses valeurs sur (-1;1). Initialement introduite pour modéliser les corrélations entre des variables continues, son extension au cas discret implique certaines restrictions. En effet, la nouvelle mesure pourrait être interprétée comme la corrélation entre les variables aléatoires continues dont la discrétisation constitue nos observations discrètes non négatives. Deux méthodes d'estimation des modèles augmentés en zéro seront présentées dans les contextes fréquentiste et bayésien basées respectivement sur le maximum de vraisemblance et l'intégration de Gauss-Hermite. Enfin, une étude de simulation permet de montrer la robustesse et les limites de notre approche.

Expérience subjective et différences individuelles dans l'intégration d'informations visuelle et kinesthésique

L’expérience subjective accompagnant un mouvement se construit a posteriori en intégrant différentes sources d’informations qui s’inter-influencent à différents moments tant avant qu’après le mouvement. Cette expérience subjective est interprétée par un modèle d’attribution bayésien afin de créer une expérience d’agentivité et de contrôle sur les mouvements de son propre corps. Afin de déterminer l’apport de l’interaction entre les paramètres considérés par le modèle d’attribution et d’investiguer la présence de disparités inter-individuelles dans la formation de l’expérience subjective du mouvement, une série de 90 pulsations simples de stimulation magnétique transcrânienne (SMT) sur le cortex moteur primaire (M1) suivi de multiples questions sur l’expérience subjective reliée au mouvement provoqué a été effectuée chez 20 participants normaux. Les données objectives du mouvement ont été recueillies par électromyographie (EMG) et capture du mouvement. Un modèle de régression a entre autres été effectué pour chaque participant afin de voir quelle proportion du jugement subjectif pouvait être expliqué par des indices objectifs et cette proportion variait grandement entre les participants. Les résultats de la présente étude indiquent la présence d’une capacité individuelle à se former des jugements subjectifs reflétant adéquatement la réalité comme en témoigne la cohérence entre les différentes mesures d’acuité et plusieurs variables mesurant l’expérience subjective.

An Alternative Approach To Computer System Security Monitoring And Enhancement Through System Call Sequence Analysis

Modern computer systems are plagued with stability and security problems: applications lose data, web servers are hacked, and systems crash under heavy load. Many of these problems or anomalies arise from rare program behavior caused by attacks or errors. A substantial percentage of the web-based attacks are due to buffer overflows. Many methods have been devised to detect and prevent anomalous situations that arise from buffer overflows. The current state-of-art of anomaly detection systems is relatively primitive and mainly depend on static code checking to take care of buffer overflow attacks. For protection, Stack Guards and I-leap Guards are also used in wide varieties.This dissertation proposes an anomaly detection system, based on frequencies of system calls in the system call trace. System call traces represented as frequency sequences are profiled using sequence sets. A sequence set is identified by the starting sequence and frequencies of specific system calls. The deviations of the current input sequence from the corresponding normal profile in the frequency pattern of system calls is computed and expressed as an anomaly score. A simple Bayesian model is used for an accurate detection.Experimental results are reported which show that frequency of system calls represented using sequence sets, captures the normal behavior of programs under normal conditions of usage. This captured behavior allows the system to detect anomalies with a low rate of false positives. Data are presented which show that Bayesian Network on frequency variations responds effectively to induced buffer overflows. It can also help administrators to detect deviations in program flow introduced due to errors.

Poverty targeting and income impact of subsidised credit on accessed households in the Northern Mountainous Region of Vietnam

This paper uses the data of 1338 rural households in the Northern Mountainous Region of Vietnam to examine the extent to which subsidised credit targets the poor and its impacts. Principal Component Analysis and Propensity Score Matching were used to evaluate the depth of outreach and the income impact of credit. To address the problem of model uncertainty, the approach of Bayesian Model Average applied to the probit model was used. Results showed that subsidised credit successfully targeted the poor households with 24.10% and 69.20% of clients falling into the poorest group and the three bottom groups respectively. Moreover, those who received subsidised credit make up 83% of ethnic minority households. These results indicate that governmental subsidies are necessary to reach the poor and low income households, who need capital but are normally bypassed by commercial banks. Analyses also showed that ethnicity and age of household heads, number of helpers, savings, as well as how affected households are by shocks were all factors that further explained the probability at which subsidised credit has been assessed. Furthermore, recipients obtained a 2.61% higher total income and a 5.93% higher farm income compared to non-recipients. However, these small magnitudes of effects are statistically insignificant at a 5% level. Although the subsidised credit is insufficient to significantly improve the income of the poor households, it possibly prevents these households of becoming even poorer.