Neste trabalho, trˆes modelos foram ajustados a um conjunto de dados obtido de um ensaio de controle biol´ogico para Diatraea saccharalis, uma praga comum em planta¸c˜oes de cana-de-a¸c´ucar. Usando a distribui¸c˜ao binomial como modelo de probabilidade, um ajuste adequado n˜ao pode ser obtido, devido `a superdispers˜ao gerada pela variabililidade dos dados e pelo excesso de zeros. Nesse caso, o modelo binomial inflacionado de zeros (ZIB) superdisperso ´e mais flex´ývel e eficiente para a modelagem desse tipo de dados. Entretanto, quando o interesse maior est´a sobre os valores positivos das propor¸c˜oes, pode-se utilizar o modelo binomial truncado superdisperso. Uma abordagem alternativa eficiente que foi utilizada para a modelagem desse tipo de dados foi a Bayesiana, sendo o ajuste do modelo realizado usando as t´ecnicas de simula¸c˜ao Monte Carlo em Cadeias de Markov, atrav´es do algoritmo Metropolis-Hastings e a sele¸c˜ao dos modelos foi feita usando o DIC (Deviance Information Criterion) e o fator de Bayes. Os modelos foram implementados no procedimento IML (Iteractive Matrix Linear) do programa SAS (Statistical Analysis System) e no programa WinBUGS e a convergˆencia das estimativas foi verificada atrav´es da an´alise gr´afica dos valores gerados e usando os diagn´osticos de Raftery & Lewis e de Heidelberger & Welch, implementado no m´odulo CODA do programa R. / In general the standard binomial regression models do not fit well to proportion data from biological control assays, manly when there is excess of zeros and overdispersion. In this work a zero-inflated binomial model is applied to a data set obtained from a biological control assay for Diatraea saccharalis, a commom pest in sugar cane. A parasite (Trichogramma galloi) was put to parasitize 128 eggs of the Anagasta kuehniella, an economically suitable alternative host (Parra, 1997), with a variable number of female parasites (2, 4, 8,..., 128), each with 10 replicates in a completely randomized experiment. When interest is only in the positive proportion data, a model can be based on the truncated binomial distribution. A Bayesian procedure was formulated using a simulation technique (Metropolis Hastings) for estimation of the posterior parameters of interest. The convergence of the Markov Chain generated was monitored by visualization of the trace plot and using Raftery & Lewis and Heidelberg & Welch diagnostics presented in the module CODA of the software R.

Made available in DSpace on 2016-03-15T19:40:15Z (GMT). No. of bitstreams: 1 Ariane Cristina Ramello de Carvalho.pdf: 542187 bytes, checksum: b329ccdc42149aed0374b8fe13c088c7 (MD5) Previous issue date: 2014-02-04 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Given the scarcity of well-validated instruments in Brazil capable of measuring local coherence ability in children-found the need to undertake a study to quantitatively reveal the performance of linguistic processing, in respect of local coherence in a population of normal children of the network mainstream education. The ability local coherence is essential for good reading comprehension and is characterized by the production of inferences between a sentence and the other from the reading of a text. In this study we used the Local Coherence Inference Test translated into Portuguese, which was applied in 50 normal children of elementary school, aged 9-13 years, with the objective of determining if there is an age effect on the performance of this group on the Local Coherence Inference Test translated into Portuguese. Results showed that children 9 years of age showed some reduction in their performance in the test, however, the discrepancy in the number of correct responses between the groups was not significant, which may indicate that children 9 years old can properly access the ability of local Coherence, but the more practice reading, knowledge about the theme and most relevant topic lexical repertoire child will be able to establish an more appropriate inference from a sentence and another. / Avaliação de coerência local e inferência por meio do Local Coherence Inference Test traduzido para a língua portuguesa Em face da escassez de instrumentos devidamente validados no Brasil capazes de medir habilidade de coerência local em crianças, constatou-se a necessidade de realizar um estudo que revele quantitativamente o desempenho do processamento linguístico, no tocante a coerência local numa população de crianças normais da rede de ensino regular. A habilidade coerência local é imprescindível para uma boa compreensão textual e é caracterizada pela produção de inferências entre uma sentença e outra à partir da leitura de um texto. Neste estudo utilizou-se o Local Coherence Inference Test traduzido para a língua portuguesa, o qual foi aplicado em 50 crianças normais, do Ensino Fundamental, na faixa etária de 9 a 13 anos, com o objetivo de verificar se há efeito de idade no desempenho deste grupo no Local Coherence Inference Test traduzido para a língua portuguesa. Os resultados mostraram que as crianças de 9 anos de idade apresentaram sensível redução no desempenho do teste, porém, a discrepância do número de acertos entre os grupos etários não foi significativa, o que pode indicar que crianças com 9 anos de idade já conseguem acessar adequadamente a habilidade de coerência local, porém, quanto mais treino de leitura, conhecimento sobre o tema lido e maior o repertório lexical mais competente a criança será em estabelecer uma inferência entre uma sentença e outra.

The lasso is a popular tool that can be used for variable selection and esti- mation, however, classical statistical inference cannot be applied for its estimates. In this thesis the classical and the group lasso is described together with effici- ent algorithms for the solution. The key part is dedicated to the post-selection inference for the lasso estimates where we explain why the classical inference is not suitable. Three post-selection tests for the lasso are described and one test is proposed also for the group lasso. The tests are compared in simulations where finite sample properties are examined. The tests are further applied on a practical example. 1

No description available.

Orientadores: Caio Lucidius Naberezny Azevedo, Filidor Edilfonso Vilca Labra / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-26T22:33:37Z (GMT). No. of bitstreams: 1 Chaves_NathaliaLima_M.pdf: 3044792 bytes, checksum: 8fea3cd9d074997b605026a7a4526c35 (MD5) Previous issue date: 2015 / Resumo: A classe de modelos Birnbaum-Saunders (BS) foi desenvolvida a partir de problemas que surgiram na área de confiabilidade de materiais. Tais problemas, em geral, são ligados ao estudo de fadiga de materiais. No entanto, nos últimos tempos, essa classe de modelos tem sido aplicada em áreas fora do referido contexto como, por exemplo, em ciências da saúde, ambiental, florestal, demográficas, atuariais, financeira, entre outras, devido à sua grande versatilidade. Neste trabalho desenvolvemos a distribuição Birnbaum-Saunders (BS) baseada na normal assimétrica padrão sob a parametrização centrada (BSNAC) que, além de representar uma extensão da distribuição BS usual, apresenta diversas vantagens em relação à distribuição BS baseada na distribuição normal assimétrica sob a parametrização usual. Desenvolvemos também um modelo de regressão linear log-Birnbaum-Saunders. Apresentamos, tanto para a distribuição BSNAC quanto para o respectivo modelo de regressão, diversas propriedades. Desenvolvemos procedimentos de estimação sob os enfoques frenquentista e bayesiano, bem como ferramentas de diagnóstico para os modelos propostos, contemplando análise residual e medidas de influência. Realizamos estudos de simulação, considerando diferentes cenários, com o intuito de comparar as estimativas frequentistas e bayesianas, bem como avaliar o desempenho das medidas de diagnóstico. A metodologia aqui proposta foi ilustrada tanto com dados provenientes de estudos de simulação, quanto com conjuntos de dados reais / Abstract: The class of Birnbaum-Saunders (BS) models was developed from problems that arose in the field of material reliability. These problems generally are related to the study of material fatigue. However, in the last years, this class of models has been applied in areas outside that context, such as in health sciences, environmental, forestry, demographic, actuarial, financial, among others, due to its great versatility. In this work, we developed the skew-normal Birnbaum-Saunders distribution under the centered parameterization (BSNAC), which also represents an extension of the usual BS distribution and presents several advantages over the BS distribution based on the skew-normal distribution under the usual parameterization. We also developed a log-Birnbaum-Saunders linear regression model. We present several properties of both BSNAC distribution and the related regression model. We develop estimation procedures under the frequentist and Bayesian approaches, as well as diagnostic tools for the proposed models, contemplating residual analysis and measures of influence. We conducted simulation studies considering different scenarios, in order to compare the frequentist and Bayesian estimates and evaluate the performance of diagnostic measures. The methodology proposed here is illustrated with data sets from both simulation studies and real data sets / Mestrado / Estatistica / Mestra em Estatística

Nous évoluons dans un monde incertain. De ce fait, notre survie dépend de notre capacité à prendre rapidement des décisions, et ce de manière fiable et adaptative. Il est possible de mieux comprendre cette capacité en considérant la perception comme un processus d’inférence probabiliste au cours duquel les informations sensorielles sont combinées à nos attentes pour produire une interprétation plausible de notre environnement. Les théories récentes de psychiatrie computationnelle suggèrent par ailleurs que la grande variabilité des troubles psychiatriques, au rang desquelles figure la schizophrénie, pourrait résulter d’une altération de ces mêmes processifs prédictifs. L’Inférence Circulaire est l’une de ces théories. Ce cadre de pensée stipule qu’une propagation incontrôlée d’information dans la hiérarchie corticale pourrait générer des percepts ou des croyances aberrantes. Afin d’explorer le rôle joué par l’Inférence Circulaire en condition normale ou pathologique, ce travail de thèse s’est appuyé sur des tâches de prise de décision en conditions perceptives ambigües. Dans une première partie, nous nous sommes intéressés au rôle joué par la circularité dans la perception bistable. Le phénomène de bistabilité survient lorsque deux interprétations se succèdent à intervalle régulier pour un même percept. Nous présentons les résultats d’une tâche conduite en population saine où nous avons manipulé les informations sensorielles et à priori utilisées par les participants lors de la visualisation d’un cube de Necker (article 1). Nous avons pu montrer un effet propre à chaque manipulation, mais également une interaction entre ces deux sources d’information, incompatible avec une intégration Bayésienne optimale. Résultat confirmé par la comparaison de divers modèles computationnels ajustés aux données, qui a pu mettre en évidence la supériorité de l’Inférence Circulaire sur les modèles Bayésiens classiques. Nous avons ensuite voulu tester un modèle fonctionnel de la bistabilité (article 2). Nous avons donc dérivé la dynamique du modèle et montré que la présence de boucles descendantes dans la hiérarchie corticale, transformait ce qui était jusque là un intégrateur imparfait du bruit sensoriel en modèle à attracteur bistable. Ce modèle ne reproduit pas seulement le phénomène de bistabilité, mais également l’ensemble de ces caractéristiques phénoménologiques. Dans un 3ème article, nous avons testé une prédiction, notamment en cas de présentation discontinue d’un stimulus bistable. Deux expériences complémentaires utilisant un paradigme de présentation intermittente du cube de Necker ont donc été conduites en population générale. Nos résultats étaient compatible avec les prédictions faites par le modèle de l’Inférence Circulaire Dynamique, suggérant que la circularité puisse être un mécanisme générique à l’origine de notre façon de voir le monde. Dans la seconde partie de ce travail, nous avons étudié l’Inférence Circulaire en condition pathologique, notamment lors d’expériences psychotiques (schizophrénie, psychédéliques). Nous avons utilisé la perception bistable pour explorer les mécanismes computationnels à l’œuvre dans la schizophrénie (article 4,5). Nous avons comparé les performances de patients présentant des symptômes psychotiques à des témoins sains appariés lors d’une tâche de perception bistable. Nous avons pu montrer chez les patients une amplification des informations sensorielles combinée à une surestimation de la volatilité environnementale. Enfin nous terminons ce travail en proposant une approche transversale de l’effet des psychédéliques (article 6), sur la base des résultats précédents et de la spécificité clinique de ces expériences sensorielles cross-modales, afin de relier l’échelle macroscopique (i.e., comportement et phénoménologie), mésoscopique (i.e., les boucles inférentielles) et microscopique (i.e., les différents neurotransmetteurs impliqués aboutissant à un microcircuit canonique). / We live in an uncertain world, yet our survival depends on how quickly and accurately we can make decisions and act upon them. To address this problem, modern neuroscience reconceptualised perception as an inference process, in which the brain combines sensory inputs and prior expectations to reconstruct a plausible image of the world. In addition to that, influential theories in the emerging field of computational psychiatry suggest that various psychiatric disorders, including schizophrenia, could be the outcome of impaired predictive processing. Among those theories, the circular inference framework suggests that an unconstrained propagation of information in the cortex, underlain by an excitatory to inhibitory imbalance, can generate false percepts and beliefs, similar to those exhibited by schizophrenia patients. In the present thesis, we probed the role of circular inference from normal to pathological brain functioning, gaining insights from perceptual decision making in the presence of high ambiguity. In the first part of the thesis, we focused on the role of circularity in bistable perception in the general population. Bistability occurs when two mutually exclusive interpretations compete and switch as dominant percepts every few seconds. In a 1st article, we manipulated sensory evidence and priors in a Necker cube task, asking how the brain combines low-level and high-level information to form perceptual interpretations. We found a significant effect of each manipulation but also an interaction between the two, a finding incompatible with Bayes optimal integration. Bayesian model comparison further supported this observation, showing that a circular inference model outperformed purely Bayesian models. Having established a link between circular inference and bistable perception, we then put forward a functional theory of bistability, based on circularity (2nd article). In particular, we derived the dynamics of a dynamical circular inference model, showing that descending loops (i.e. a form of circularity resulting in aberrant amplification of the priors) transform what is normally a leaky integration of noisy evidence into a bistable attractor with two highly trusted stable states. Importantly, this model can explain both the existence and the phenomenological properties of bistable perception, making a number of testable predictions. Finally, in a 3rd article, we tested one of the model’s predictions, namely the perceptual behaviour when the stimulus is presented discontinuously. We ran two Necker cube experiments using a novel intermittent-presentation methodology, and we calculated the stabilisation curves (i.e. persistence as a function of blank durations). We found that participants’ behaviour was compatible with the model’s prediction for a system with descending loops, suggesting that circularity constitutes a general mechanism that shapes the way healthy individuals perceive the world. In the second part, we studied circular inference in pathological conditions related to psychosis. We notably focused on two varieties of the psychotic experience, namely schizophrenia-related psychosis and drug-induced psychosis. After discussing the links between behaviour, aberrant message-passing and the corresponding neural networks (4th article), we used bistable perception to probe the computational mechanisms underlying schizophrenia in a 5th article. We compared patients with prominent positive symptoms with matched healthy controls in two bistable perception tasks. Our results suggest an enhanced amplification of sensory inputs in patients, combined with an overestimation of the environmental volatility. In the last article (6th), we delineated a multiscale account of psychedelics, ultimately linking the macroscale (i.e. phenomenological considerations such as the crossmodal character of the psychedelics experience), the mesoscale (i.e. loops) and the microscale (i.e. neuromodulators and canonical microcircuits).

This master's thesis deals with possible applications of Bayesian networks. The theoretical part is mainly of mathematical nature. At first, we focus on general probability theory and later we move on to the theory of Bayesian networks and discuss approaches to inference and to model learning while providing explanations of pros and cons of these techniques. The practical part focuses on applications that demand learning a Bayesian network, both in terms of network parameters as well as structure. These applications include general benchmarks, usage of Bayesian networks for knowledge discovery regarding the causes of criminality and exploration of the possibility of using a Bayesian network as a spam filter.

Introducing new financial legislation to financial markets require caution to achieve the intended outcome. This thesis aims to investigate whether or not the newly installed revised Markets in Financial Instruments Directive- the MIFID II regulation - temporally influenced the trading stock volume levels of Nasdaq Stockholm during its introduction to the Swedish stock market. A first approach of a generalized Negative Binomial model is carried out on aggregated data, followed by an individual Fixed Effects model in an attempt to eliminate omitted variable bias caused by missing unobserved variables for the individual stocks. The aggregated data is attained by taking the equally weighted average of the trading volume and adjusting for seasonality through Seasonal and Trend decomposition using Loess in combination with a regression model with ARIMA errors to mitigate calendar effects. Due to robustness of the aggregated data, the Negative Binomial model manage to capture significant effects of the regulation on the Small Cap. segment, even though clusters of the data show signs of divergent reactions to MIFID II. Since the Fixed Effects model operate on non-aggregated TSCS data and because of the varying effects on each stock the Fixed Effect model fails in its attempt to do the same. / Implementation av nya finansiella regelverk på finansmarknaden kräver aktsamhet för att uppnå de tilltänka målen. Det här arbetet undersöker huruvida MIFID II regleringen orsakade en temporär medelvärdesskiftning av de handlade aktievolymerna på Nasdaq Stockholm under regelverkets introduktion på den svenska marknaden. Först testas en generaliserad Negative Binomial regression applicerat på aggregerad data, därefter en individuell Fixed Effects modell för att försöka eliminera fel på grund av saknade, okända variabler. Det aggrigerade datasettet erhålls genom att ta genomsnittet av handelsvolymerna och justera dessa för sässongsmässiga mönster med metoden STL i kombination med regression med ARIMA residualer för att även ta hänsyn till kalender relaterade effekter. Eftersom den aggrigerade datan är robust lyckas the Negative Binomial regressionen fånga signifikanta effekter av regleringen för Small Cap. segmentet trots att datat uppvisar tecken på att subgrupper inom segmentet reagerat väldigt olika på den nya regleringen. Eftersom Fixed Effects modellen är applicerad på icke-aggrigerad TSCS data och pågrund av den varierande effekten på de individuella aktierna lyckas inte denna modell med detta.

The Vagus nerve has shown to play an important role regarding inflammatory diseases, regulating the production of proteins that mediate inflammation. Two important such proteins are the pro-inflammatory cytokines, TNF and IL-1β. This thesis makes use of Vagus nerve recordings, where TNF and IL-1β are subsequently injected in mice, with the aim to see if cytokine-specific information can be extracted. To this end, a type of semi-supervised learning approach is applied, where the observed waveform-data are modeled using a conditional probability distribution. The conditioning is done based on an estimate of how often each observed waveform occurs and local maxima of the conditional distribution are interpreted as candidate-waveforms to encode cytokine information. The methodology yields varying, but promising results. The occurrence of several candidate waveforms are found to increase substantially after exposure to cytokine. Difficulties obtaining coherent results are discussed, as well as different approaches for future work. / Vagusnerven har visat sig spela en viktig roll beträffande inflammatoriska sjukdomar. Denna nerv reglerar produktionen av inflammatoriska protein, som de inflammationsfrämjande cytokinerna TNF och IL-1β. Detta arbete använder sig av elektroniska mätningar av Vagusnerven i möss som under tiden blir injicerade med de två cytokinerna TNF och IL-1β. Syftet med arbetet är att undersöka om det är möjligt att extrahera information om de specifika cytokinerna från Vagusnervmätningarna. För att uppnå detta designar vi en semi-vägledd lärandemetod som modellerar dem observerade vågformerna med en betingad sannolikhetsfunktion. Betingandet baseras på en uppskattning av hur ofta varje enskild vågform förekommer och lokala maximum av den betingade sannolikhetsfunktionen tolkas som möjliga kandidat-vågformer att innehålla cytokin-information. Metodiken ger varierande, men lovande resultat. Förekomsten av flertalet kandidat-vågformer har en tydlig ökning efter tidpunkten för cytokin-injektion. Vidare så diskuteras svårigheter i att uppnå konsekventa resultat för alla mätningar, samt olika möjligheter för framtida arbete inom området.

No description available.