Siga este enlace para ver otros tipos de publicaciones sobre el tema: Population Monte Carlo.
Tesis sobre el tema "Population Monte Carlo"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 49 mejores tesis para su investigación sobre el tema "Population Monte Carlo".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
1
Bakra, Eleni. "Aspects of population Markov chain Monte Carlo and reversible jump Markov chain Monte Carlo". Thesis, University of Glasgow, 2009. http://theses.gla.ac.uk/1247/.
Texto completo
2
Anderson, Eric C. "Monte Carlo methods for inference in population genetic models /". Thesis, Connect to this title online; UW restricted, 2001. http://hdl.handle.net/1773/6368.
Texto completo
3
Rousset, Mathias. "Méthodes de "Population Monte-Carlo'' en temps continu est physique numérique". Toulouse 3, 2006. http://www.theses.fr/2006TOU30251.
Texto completoResumen
Dans cette thèse, nous nous intéressons aux méthodes numériques probabilistes dites de Population Monte-Carlo, du point de vue du temps continu. Ces méthodes PMC se ramènent au calcul séquentiel de moyennes pondérées de trajectoires Markoviennes. Nous démontrons la convergence (vers la fonction propre principale des opérateurs de Schrödinger) en temps long de la variance et du biais de cette méthode avec la bonne vitesse en 1/N. Ensuite, nous considérons le problème de l'échantillonnage séquentiel d'un flot continu de mesures de Boltzmann. Pour cela, à partir d'une dynamique Markovienne arbitraire, nous associons une dynamique renversée dans le temps dont la loi pondérée par une moyenne trajectorielle de Feynman-Kac explicitement calculable redonne la dynamique initiale ainsi que la mesure de Boltzmann à calculer. Enfin, nous généralisons ce problème au cas où la dynamique est due à l'évolution dans le temps de contraintes rigides sur les configurations possibles du processus. Nous calculons exactement les poids associés, qui font intervenir la courbure locale des sous-variétés générées par les contraintes.In this dissertation, we focus on stochastic numerical methods of Population Monte-Carlo type, in the continuous time setting. These PMC methods resort to the sequential computation of averages of weighted Markovian paths. The practical implementation rely then on the time evolution of the empirical distribution of a system of N interacting walkers. We prove the long time convergence (towards Schrödinger groundstates) of the variance and bias of this method with the expected 1/N rate. Next, we consider the problem of sequential sampling of a continuous flow of Boltzmann measures. For this purpose, starting with any Markovian dynamics, we associate a second dynamics in reversed time whose law (weighted by a computable Feynman-Kac path average) gives out the original dynamics as well as the target Boltzmann measure. Finally, we generalize the latter problem to the case where the dynamics is caused by evolving rigid constraints on the positions of the process. We compute exactly the associated weights, which resorts to the local curvature of the manifold defined by the constraints
4
Ding, Jie. "Monte Carlo Pedigree Disequilibrium Test with Missing Data and Population Structure". The Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=osu1218475579.
Texto completo
5
Fan, Gailing. "Galaxy radio pulsar population modelling and magellanic clouds radio pulsar survey /". Hong Kong : University of Hong Kong, 2002. http://sunzi.lib.hku.hk/hkuto/record.jsp?B25059294.
Texto completo
6
Lunn, David Jonathan. "The application of Markov chain Monte Carlo techniques to the study of population pharmacokinetics". Thesis, University of Manchester, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.488145.
Texto completo
7
Camacho, Díaz Judit. "Monte Carlo simulations of the population of single and binary white dwarfs of our galaxy". Doctoral thesis, Universitat Politècnica de Catalunya, 2014. http://hdl.handle.net/10803/145924.
Texto completoResumen
Since white dwarfs are the final stage of the evolution of the vast majority of stars, they carry important information about the chemical evolution of our Galaxy, its star formation rate, and its structure and dynamics. This thesis pays attention to two related but distinct astrophysical problems involving white dwarfs.
The first of these problems concern the nature and the location of the microlensing events towards the Large Magellanic Clouds (LMC), which still remains a mystery. The main observational groups, MACHO and EROS, are in dispute each, yet agreement has now been reached in some of the most important points.
The second of the problems we address in this thesis is an open problem as well. Close compact binaries are at the heart of several interesting phenomena in our Galaxy as well. Close compact binaries are formed through at least one common envelope episode. Even though the basics concepts of the evolution during a common envelope phase are rather simple, the details are still far from being well understood.
To shed light on these problems, we used an existing Monte Carlo simulator. We expanded this simulator integrating the most up-to-date white dwarfs cooling models as well as detailed modeling of our Galaxy and the LMC in order to mimic both the MACHO and EROS experiments. Additionally, we included the red dwarf population and performed a joint analysis of the contributions of both populations to the dark matter content of our Galaxy. Moreover, we studied the contribution of the subpopulation of white dwarfs with hydrogen-deficient atmospheres.
On the other hand, our Monte Carlo code has been expanded to deal with those systems composed by a white dwarf and a main sequence star, which have evolved through a common episode. A detailed implementation of several different physical processes, including a full description of the mass transfer episode, a complete treatment of the Roche lobe overflow episode, gravitational tides and orbital evolution of the binary system, was performed. Furthermore, in our treatment we carefully included all the different selection criteria and observational biases. This allowed us to make a meaningful comparison with the available data, besides examining the role played by the binding energy parameter and by the common envelope parameter, not to mention the role played by the distribution of secondary masses of the binary systems.
The results of our Monte Carlo simulations of the microlensing experiments show agreement with the findings of the EROS and MACHO survey. Our findings show that neither white dwarfs nor red dwarfs can be major contributors to the microlensing depth towards the LMC. These facts reinforce the idea, previously pointed by others studies, that the optical depth found by the MACHO survey is highly likely an overestimate, probably due to contamination of self-lensing objects, amid other possible explanations.
Concerning the second point of this thesis, our Monte Carlo simulations correctly reproduce the properties of the observed population of post-common envelope white dwarf plus main sequence binaries, once biases are taken into account. The best-fit models are obtained with fractions less than ~20% of the internal energy contributing to the ejection of the star progenitor¿s envelope, and values for the common-envelope efficiency parameter less than ~0.3.
To conclude, the work presented in this thesis poses an important step forward not only in constraining the microlensing discoveries, but also in validating models for the observed white-dwarf populations of our Galaxy.
8
范改玲 y Gailing Fan. "Galaxy radio pulsar population modelling and magellanic clouds radio pulsar survey". Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2002. http://hub.hku.hk/bib/B31243058.
Texto completo
9
Louw, Markus. "A population Monte Carlo approach to estimating parametric bidirectional reflectance distribution functions through Markov random field parameter estimation". Doctoral thesis, University of Cape Town, 2009. http://hdl.handle.net/11427/5179.
Texto completoResumen
In this thesis, we propose a method for estimating the parameters of a parametric bidirectional reflectance distribution function (BRDF) for an object surface. The method uses a novel Markov Random Field (MRF) formulation on triplets of corner vertex nodes to model the probability of sets of reflectance parameters for arbitrary reflectance models, given probabilistic surface geometry, camera, illumination, and reflectance image information. In this way, the BRDF parameter estimation problem is cast as a MRF parameter estimation problem. We also present a novel method for estimating the MRF parameters, which uses Population Monte Carlo (PMC) sampling to yield a posterior distribution over the parameters of the BRDF. This PMC based method for estimating the posterior distribution on MRF parameters is compared, using synthetic data, to other parameter estimation methods based on Markov Chain Monte Carlo (MCMC) and Levenberg-Marquardt nonlinear minimization, where it is found to have better results for convergence to the known correct synthetic data parameter sets than the MCMC based methods, and similar convergence results to the LM method. The posterior distributions on the parametric BRDFs for real surfaces, which are represented as evolved sample sets calculated using a Population Monte Carlo algorithm, can be used as features in other high-level vision material or surface classification methods. A variety of probabilistic distances between these features, including the Kullback-Leibler divergence, the Bhattacharyya distance and the Patrick-Fisher distance is used to test the classifiability of the materials, using the PMC evolved sample sets as features. In our experiments on real data, which comprises 48 material surfaces belonging to 12 classes of material, classification errors are counted by comparing the 1-nearest-neighbour classification results to the known (manually specified) material classes. Other classification error statistics such as WNN (worst nearest neighbour) are also calculated. The symmetric Kullback-Leibler divergence, used as a distance measure between the PMC developed sample sets, is the distance measure which gives the best classification results on the real data, when using the 1-nearest neighbour classification method. It is also found that the sets of samples representing the posterior distributions over the MRF parameter spaces are better features for material surface classification than the optimal MRF parameters returned by multiple-seed Levenberg-Marquardt minimization algorithms, which are configured to find the same MRF parameters. The classifiability of the materials is also better when using the entire evolved sample sets (calculated by PMC) as classification features than it is when using only the maximum a-posteriori sample from the PMC evolved sample sets as the feature for each material. It is therefore possible to calculate usable parametric BRDF features for surface classification, using our method.
10
Li, Qianqiu. "Bayesian inference on dynamics of individual and population hepatotoxicity via state space models". Connect to resource, 2005. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1124297874.
Texto completoResumen
Thesis (Ph. D.)--Ohio State University, 2005.Title from first page of PDF file. Document formatted into pages; contains xiv, 155 p.; also includes graphics (some col.). Includes bibliographical references (p. 147-155). Available online via OhioLINK's ETD Center
11
Goins, David Matthew. "Population Cross-Validity Estimation and Adjustment for Direct Range Restriction: A Monte Carlo Investigation of Procedural Sequences to Achieve Optimal Cross-Validity". TopSCHOLAR®, 2010. http://digitalcommons.wku.edu/theses/165.
Texto completoResumen
The current study employs Monte Carlo analyses to evaluate the effectiveness of various statistical procedures for determining specific values of interest within a population of 1,000,000 cases. Specifically, the proper procedures for addressing the opposing effects of direct range restriction and validity overestimation were assessed through a comparison of multiple correlation coefficients derived using various sequences of procedures in randomly drawn samples. A comparison of the average bias associated with these methods indicated that correction for range restriction prior to the application of a validity overestimation adjustment formula yielded the best estimate of population parameters over a number of conditions. Additionally, similar methods were employed to assess the effectiveness of the standard ΔR2F-test for determining, based on characteristics of the derivation sample, the comparative superiority of either optimally or unit weighted composites in future samples; this procedure was largely ineffective under the conditions employed in the current study.
12
Zijerveld, Leonardus Jacobus Johannes. "Integrated modelling and Bayesian inference applied to population and disease dynamics in wildlife : M.bovis in badgers in Woodchester Park". Thesis, University of Edinburgh, 2013. http://hdl.handle.net/1842/7733.
Texto completoResumen
Understanding demographic and disease processes in wildlife populations tends to be hampered by incomplete observations which can include significant errors. Models provide useful insights into the potential impacts of key processes and the value of such models greatly improves through integration with available data in a way that includes all sources of stochasticity and error. To date, the impact on disease of spatial and social structures observed in wildlife populations has not been widely addressed in modelling. I model the joint effects of differential fecundity and spatial heterogeneity on demography and disease dynamics, using a stochastic description of births, deaths, social-geographic migration, and disease transmission. A small set of rules governs the rates of births and movements in an environment where individuals compete for improved fecundity. This results in realistic population structures which, depending on the mode of disease transmission can have a profound effect on disease persistence and therefore has an impact on disease control strategies in wildlife populations. I also apply a simple model with births, deaths and disease events to the long-term observations of TB (Mycobacterium bovis) in badgers in Woodchester Park. The model is a continuous time, discrete state space Markov chain and is fitted to the data using an implementation of Bayesian parameter inference with an event-based likelihood. This provides a flexible framework to combine data with expert knowledge (in terms of model structure and prior distributions of parameters) and allows us to quantify the model parameters and their uncertainties. Ecological observations tend to be restricted in terms of scope and spatial temporal coverage and estimates are also affected by trapping efficiency and disease test sensitivity. My method accounts for such limitations as well as the stochastic nature of the processes. I extend the likelihood function by including an error term that depends on the difference between observed and inferred state space variables. I also demonstrate that the estimates improve by increasing observation frequency, combining the likelihood of more than one group and including variation of parameter values through the application of hierarchical priors.
13
Gullón, Juanes Miguel. "Population Synthesis of isolated Neutron Stars". Doctoral thesis, Universidad de Alicante, 2015. http://hdl.handle.net/10045/53162.
Texto completoResumen
Neutron Stars present a wide variety from the observational point of view. The advent of new and powerful detectors and instruments has opened a new era where the classical picture of neutrons stars seen as radio-pulsars has been modified with new classes such as magnetars, X-ray Isolated Neutron Stars (XINSs) or Central Compact Objects (CCOs) in Supernova Remnants . In addition to the more than 2500 sources detected in the radio band, more than two hundred have also been detected as X-ray and gamma-ray sources. This number is expected to increase in the near future. Despite this apparent diversity, some studies demand a theory able to explain the different classes in terms of the same physical scenario (Kaspi, 2010), in which the evolution of the magnetic field appears to play an important role (Viganò et al., 2013). The Population Synthesis of Neutron Stars, which is the central subject of this thesis, is an interesting approach to understand the problem, as both intrinsic properties and observational biases are taken into account. These technique is based on Monte Carlo methods, applied to simulate the whole population of neutron stars. The main objective of the thesis has been to perform a multi-wavelength study of the different populations of Neutron Stars focusing in the effects of magneto-thermal evolution. This report consists of a global summary of the objectives, methods and main results of the thesis. It is structured as follows. The first chapter gives an introduction to Neutron Stars. Chapter two is a description of the method of Population Synthesis of Neutron Stars. In chapter three a global discussion of the main results is presented. Chapter four closes the report with the conclusions. An appendix is also included which constitutes a description of a method based on the pulsar current analysis.
14
Pianucci, Marcela Navarro. "Uma proposta para a obtenção da população sintética através de dados agregados para modelagem de geração de viagens por domicílio". Universidade de São Paulo, 2016. http://www.teses.usp.br/teses/disponiveis/18/18143/tde-24102016-154347/.
Texto completoResumen
A estimativa de viagens por domicílio é fundamental para a tomada de decisões relativas ao planejamento urbano e de transportes. Em geral, a obtenção destas informações é por meio de modelos tradicionais como o modelo clássico de quatro etapas, e a primeira etapa do modelo é a geração de viagens. Entretanto, modelos clássicos apresentam inúmeras falhas, muitas delas relacionadas a suposições prévias matemáticas (normalidade ou continuidade da variável dependente). Desta forma, surge a necessidade de testar outras técnicas de modo a minimizar as falhas apresentadas pelos modelos clássicos e utilizá-las como uma ferramenta auxiliar, como por exemplo, as Redes Neurais Artificiais (RNAs), que podem ser aplicáveis na modelagem de problemas complexos e não lineares na área de engenharia de transportes, pois apresentam capacidade de aprendizagem, adaptação e generalização. Assim, para estimar viagens por domicílio, seja pela modelagem tradicional ou pela modelagem RNA são necessários dados desagregados dos domicílios, incluindo dados dos indivíduos, como as atividades diárias que exerce me dados sócio demográficos, etc. Esses dados são geralmente obtidos por uma Pesquisa O/D, que fornece um banco de dados detalhado sobre o comportamento de viagem da população de uma cidade. No entanto, a maioria das cidades enfrenta problemas para a aquisição desses dados, uma vez que este tipo de pesquisa possui alto custo de preparação, execução, processamento e análise. Portanto, percebe-se a necessidade de novos métodos que forneçam dados confiáveis e com baixo custo, para estimar a demanda por viagens, capazes de gerar resultados com rapidez, qualidade e acurácia e sem a necessidade dos dados provenientes de uma Pesquisa O/D. Devido a dificuldade de aquisição de dados desagregados, foi proposto neste trabalho, a geração da população sintética com dados agregados a partir da aplicação do Método Monte Carlo. Este trabalho tem por objetivo gerar uma população sintética baseada em dados censitários agregados e testar a adequabilidade das RNAs para estimar viagens por domicílio. Neste estudo, a modelagem tradicional foi utilizada para comparar nos resultados obtidos com a modelagem RNA, pois o objetivo não foi checar minuciosamente a qualidade dos modelos lineares, e sim, testar a adequabilidade das RNAs para estimar viagens por domicílio. A abordagem tradicional se baseou em um modelo de regressão linear enquanto que a abordagem de redes neurais consistiu da rede perceptron multi camadas. Na execução do trabalho foram calibrados quatro modelos (dois de cada abordagem) com os dados desagregados da Pesquisa O/D e foram comparados os resultados obtidos de cada abordagem. Ao final do trabalho, foi possível escolher o modelo mais adequados de cada abordagem e em seguida, foram utilizados para prever viagens por domicílio com os dados obtidos pela população sintética. Os resultados indicaram que 70% das variáveis obtidas na população sintética foram consideradas aptas para o estudo e que a estimativa de viagens por domicílio da população sintética obtida em ambos os modelos (Modelo 3-RNA) e (Modelo 4-RLM) obtiveram uma boa previsão, ou seja, mais de 70% das viagens por domicílio da população sintética foram consideradas válidas. Isso demonstrou que, o uso de da modelagem RNA é uma técnica alternativa eficiente e promissora na área de planejamento de transportes, especificamente para a previsão de viagens por domicílio.The estimated number of household travels is essential in the decision-making process related to urban and transportation planning. Usually, this information is obtained through traditional models, such as four-step classic model, for example, which has trip generation as a first step. However, classic models feature numerous failures. Many of these failures are related to mathematical prior assumptions (normality or continuity of the dependent variable). Thus, it is important to test other techniques in order to reduce the failures and use these techniques as an auxiliary tool, i.e. Artificial Neural Networks (ANN). ANN are applicable in the modeling of complex and nonlinear transportation problems, due to its learning, adaptation and generalization capacities. Thus, to estimate the number of household travel, either by traditional or by ANN models, it is required disaggregated data of the households. It might include information of individuals, as daily activities and sociodemographic information. Usually, these data are obtained by a O/D survey, which provides a detailed database of the population travel behavior of the city. However, the obtainment of this information leads to high costs of preparation, execution, processing and analysis of the data. Thus, most cities have faced problems to attain this information. Therefore, new methods of estimation providing reliable data and low cost, are required. It will enable to estimate the demand of travel, rapidly with quality and accuracy, without the need of data provided through an O/D survey. Due to the difficulty of acquiring disaggregated data, this study proposes the generation of synthetic population through aggregated data by applying the method of Monte Carlo. This study aims to generate a synthetic population based on aggregated census data, and test the suitability of ANN to estimate the number of household travels. Since the aim was not thoroughly check the quality of linear models, instead, test the suitability of ANN to estimate the number of household travels, obtained results of traditional and ANN models were compared. The traditional approach was based on a linear regression while the neural network consisted of Multilayer Perceptron network. Four models (two of each approach) were proposed and calibrated with disaggregated data of an O/D Survey. Then, the results were compared. It enabled to choose the most appropriate model of each approach. Hence, these models were used to forecast the number of household travels, using the data obtained by the synthetic population proposed. The results indicated that 70% of the variables obtained through the synthetic population, were considered suitable for the study. Besides, the estimated number of household travels of the synthetic population obtained for both models (Model 3-RNA and 4-MLR model) presented a good forecast, indicating that more than 70% of household travels of the synthetic population were considered valid. Finally, it is concluded that the use of ANN modeling is an effective and promising alternative technique in the transportation-planning field, specifically to forecast the number of household travels.
15
Rodrigues, Áttila Leães. "Dinâmica de populações: modelo predador-presa estocástico e difusivo em um reticulado". Universidade de São Paulo, 2009. http://www.teses.usp.br/teses/disponiveis/43/43134/tde-06042009-144849/.
Texto completoResumen
Estudamos o modelo predador-presa estocástico definido em uma rede com interações entre os primeiros vizinhos, cada sítio podendo assumir três estados: vazio, ocupado por presa e ocupado por predador. Introduzimos ainda um parâmetro que controla a possibilidade de difuãao dos estados, a difusão é permitida entre quaisquer estados. O modelo exibe uma fase oscilante, uma fase não-oscilante e uma fase absorvente. As duas primeiras fases possibilitam a coexistência entre as espécies biológicas enquanto na fase absorvente a rede é totalmente preenchida por presas e o sistema fica preso nessa configuração. Determinamos a linha de transição da fase não-oscilante para a fase absorvente por meio de simulações dependentes do tempo. Também, determinamos a linha de transição da fase oscilante para a fase não-oscilante através da análise das funções de autocorrelação das séries temporais de presas e predadores. Além disso, estudamos o modelo por meio de aproximações de campo médio dinâmico. Concluímos que a inclusão da difusão no modelo predador-presa leva a uma maior região de coexistência das espécies no diagrama de fases. Nossos resultados sugerem que o componente difusivo é irrevelevante quanto ao comportamento crítico, pois ele não exclui o modelo da classe de universalidade da percolação direcionada.We have studied the predator-prey stochastic model defined on a lattice with first neighbour interactions. Each site of the lattice may assume one of three states: vacant, occupied by prey and occupied by predator. We have introduced a parameter that controls the possibility of difusion among sites. The model shows an oscilating phase, a non-oscilating phase and an absorbing phase. In the first two phases the system exhibits coexistence of biological species while in the absorbing phase the lattice is filled with prey and the system becomes trapped. We have determined the transition line between the non-oscilating and absorbing phases using time-dependent simulations. We have also determined the transition lines between oscilating and non-oscilating phases using time-autocorrelation functions of the prey time-series. In addition, we have studied the model by means of dynamical mean-field aproximations. We conclude that the introduction of diffusion in the predator-prey model leads to a larger region of coexistence in the phase diagram. Our results suggest that difusion is irrelevant for the critical behavior since it does not change the universatility class of the model.
16
Parisi, Antonio. "Sampling from a variable dimension mixture model posterior". Doctoral thesis, Università degli studi di Padova, 2008. http://hdl.handle.net/11577/3425531.
Texto completoResumen
Goal of the thesis is the analysis of a real dataset concerning a biological problem that obtained an increasing interest in recent years. Commercial stocks of fish are not sufficient anymore to satisfy the global demand. Hence, fishermen are beginning to catch species living in the deep. As little is known
about these species, there is an actual risk of extinction of these species.
As it is typically difficult and expensive to gather the ages of fish, in order to implement stock management policies, it is necessary to build up reliable growth models to infer ages from length data. The lengths, if we don't observe the ages, come from a mixture distribution, in which the components are the different cohorts.
As MCMC methods are not always satisfactory for the analysis of mixture models, to estimate the parameters of the model and the number of cohorts that form the sample, it is employed a Population Monte Carlo algorithm for mixtures generalized to the case of unknown number of components.
17
Sedki, Mohammed Amechtoh. "Échantillonnage préférentiel adaptatif et méthodes bayésiennes approchées appliquées à la génétique des populations". Thesis, Montpellier 2, 2012. http://www.theses.fr/2012MON20041/document.
Texto completoResumen
Dans cette thèse, on propose des techniques d'inférence bayésienne dans les modèles où la vraisemblance possède une composante latente. La vraisemblance d'un jeu de données observé est l'intégrale de la vraisemblance dite complète sur l'espace de la variable latente. On s'intéresse aux cas où l'espace de la variable latente est de très grande dimension et comportes des directions de différentes natures (discrètes et continues), ce qui rend cette intégrale incalculable. Le champs d'application privilégié de cette thèse est l'inférence dans les modèles de génétique des populations. Pour mener leurs études, les généticiens des populations se basent sur l'information génétique extraite des populations du présent et représente la variable observée. L'information incluant l'histoire spatiale et temporelle de l'espèce considérée est inaccessible en général et représente la composante latente. Notre première contribution dans cette thèse suppose que la vraisemblance peut être évaluée via une approximation numériquement coûteuse. Le schéma d'échantillonnage préférentiel adaptatif et multiple (AMIS pour Adaptive Multiple Importance Sampling) de Cornuet et al. [2012] nécessite peu d'appels au calcul de la vraisemblance et recycle ces évaluations. Cet algorithme approche la loi a posteriori par un système de particules pondérées. Cette technique est conçue pour pouvoir recycler les simulations obtenues par le processus itératif (la construction séquentielle d'une suite de lois d'importance). Dans les nombreux tests numériques effectués sur des modèles de génétique des populations, l'algorithme AMIS a montré des performances numériques très prometteuses en terme de stabilité. Ces propriétés numériques sont particulièrement adéquates pour notre contexte. Toutefois, la question de la convergence des estimateurs obtenus parcette technique reste largement ouverte. Dans cette thèse, nous montrons des résultats de convergence d'une version légèrement modifiée de cet algorithme. Sur des simulations, nous montrons que ses qualités numériques sont identiques à celles du schéma original. Dans la deuxième contribution de cette thèse, on renonce à l'approximation de la vraisemblance et onsupposera seulement que la simulation suivant le modèle (suivant la vraisemblance) est possible. Notre apport est un algorithme ABC séquentiel (Approximate Bayesian Computation). Sur les modèles de la génétique des populations, cette méthode peut se révéler lente lorsqu'on vise uneapproximation précise de la loi a posteriori. L'algorithme que nous proposons est une amélioration de l'algorithme ABC-SMC de DelMoral et al. [2012] que nous optimisons en nombre d'appels aux simulations suivant la vraisemblance, et que nous munissons d'un mécanisme de choix de niveauxd'acceptations auto-calibré. Nous implémentons notre algorithme pour inférer les paramètres d'un scénario évolutif réel et complexe de génétique des populations. Nous montrons que pour la même qualité d'approximation, notre algorithme nécessite deux fois moins de simulations par rapport à laméthode ABC avec acceptation couramment utiliséeThis thesis consists of two parts which can be read independently.The first part is about the Adaptive Multiple Importance Sampling (AMIS) algorithm presented in Cornuet et al.(2012) provides a significant improvement in stability and Effective Sample Size due to the introduction of the recycling procedure. These numerical properties are particularly adapted to the Bayesian paradigm in population genetics where the modelization involves a large number of parameters. However, the consistency of the AMIS estimator remains largely open. In this work, we provide a novel Adaptive Multiple Importance Sampling scheme corresponding to a slight modification of Cornuet et al. (2012) proposition that preserves the above-mentioned improvements. Finally, using limit theorems on triangular arrays of conditionally independant random variables, we give a consistensy result for the final particle system returned by our new scheme.The second part of this thesis lies in ABC paradigm. Approximate Bayesian Computation has been successfully used in population genetics models to bypass the calculation of the likelihood. These algorithms provide an accurate estimator by comparing the observed dataset to a sample of datasets simulated from the model. Although parallelization is easily achieved, computation times for assuring a suitable approximation quality of the posterior distribution are still long. To alleviate this issue, we propose a sequential algorithm adapted fromDel Moral et al. (2012) which runs twice as fast as traditional ABC algorithms. Itsparameters are calibrated to minimize the number of simulations from the model
18
Reynolds, Toby J. "Bayesian modelling of integrated data and its application to seabird populations". Thesis, University of St Andrews, 2010. http://hdl.handle.net/10023/1635.
Texto completoResumen
Integrated data analyses are becoming increasingly popular in studies of wild animal populations where two or more separate sources of data contain information about common parameters. Here we develop an integrated population model using abundance and demographic data from a study of common guillemots (Uria aalge) on the Isle of May, southeast Scotland. A state-space model for the count data is supplemented by three demographic time series (productivity and two mark-recapture-recovery (MRR)), enabling the estimation of prebreeder emigration rate - a parameter for which there is no direct observational data, and which is unidentifiable in the separate analysis of MRR data. A Bayesian approach using MCMC provides a flexible and powerful analysis framework. This model is extended to provide predictions of future population trajectories. Adopting random effects models for the survival and productivity parameters, we implement the MCMC algorithm to obtain a posterior sample of the underlying process means and variances (and population sizes) within the study period. Given this sample, we predict future demographic parameters, which in turn allows us to predict future population sizes and obtain the corresponding posterior distribution. Under the assumption that recent, unfavourable conditions persist in the future, we obtain a posterior probability of 70% that there is a population decline of >25% over a 10-year period. Lastly, using MRR data we test for spatial, temporal and age-related correlations in guillemot survival among three widely separated Scottish colonies that have varying overlap in nonbreeding distribution. We show that survival is highly correlated over time for colonies/age classes sharing wintering areas, and essentially uncorrelated for those with separate wintering areas. These results strongly suggest that one or more aspects of winter environment are responsible for spatiotemporal variation in survival of British guillemots, and provide insight into the factors driving multi-population dynamics of the species.
19
Khachman, Dalia. "Adaptation de posologie des quinolones en réanimation par approche de population". Toulouse 3, 2012. http://thesesups.ups-tlse.fr/1741/.
Texto completoResumen
La première partie de la thèse a été consacrée à l'analyse pharmacocinétique de population de la ciprofloxacine chez les patients en réanimation et une optimisation, via des simulations pharmacocinétiques/pharmacodynamiques, de sa posologie par rapport aux probabilités de guérison clinique et de développement de résistance. En se basant sur le concept de la fenêtre de sélection des mutants, l'usage de la ciprofloxacine en réanimation contre P. Aeruginosa et A. Baumannii est remis en question par rapport à l'émergence de résistance. La deuxième partie, plus méthodologique, était centrée sur les outils d'évaluation de modèles en pharmacocinétique de population. Après avoir mis en évidence les limites des Visual Predictive Checks (VPC) et des outils connexes, ce travail visait à développer un nouvel outil graphique exact pour l'évaluation de ces modèles : les Visual Predictive Extended Residuals (VIPER). Les VIPER ont montré de bonnes performances comme outil d'évaluation sans présenter la plupart des lacunes liées aux outils type VPCThe first part of the thesis was devoted to the population pharmacokinetic analysis of ciprofloxacin in intensive care unit (ICU) patients and further optimisation, through pharmacokinetic/pharmacodynamic simulation studies, of ciprofloxacin dosing with respect to clinical outcome and the development of bacterial resistance. Based on the mutant selection window concept, our simulations truly question the use of ciprofloxacin for the treatment of P. Aeruginosa and A. Baumannii infections in ICU patients due to the potential for developing resistance. The second part of the thesis was more methodological and focused on model evaluation tools for population pharmacokinetic/pharmacodynamic models. After highlighting the shortcomings of the Visual Predictive Checks (VPC) and related methods, we developed a new exact graphical tool (VIsual Predictive Extended Residuals or VIPER) which showed good performances and allowed to overcome many of VPC-related issues
20
Vismara, Lilian de Souza. "Aplicação da inferência Bayesiana para a simulação da dinâmica de produção de sementes de plantas daninhas". Universidade de São Paulo, 2006. http://www.teses.usp.br/teses/disponiveis/18/18133/tde-03102006-083849/.
Texto completoResumen
No ambiente agrícola, a possibilidade de prever eventos futuros para poder estabelecer prioridades e planejar atividades são indispensáveis para um manejo adequado. Modelos matemáticos têm se tornado ferramentas valiosas para o entendimento de fenômenos e simulação de soluções de um dado sistema de interesse para diferentes condições iniciais e valores de parâmetros. O crescimento das plantas obedece a certos princípios fisiológicos que podem ser descritos, em termos quantitativos em resposta ao meio ambiente, através de equações matemáticas. Nos agrosistemas, a dinâmica da população de plantas daninhas pode ser descrita por modelos matemáticos que relacionam as densidades de sementes produzidas e de plântulas em áreas de cultivo. Os valores dos parâmetros dos modelos podem ser inferidos diretamente de experimentação e análise estatística, ou extraídos da literatura. O presente trabalho tem por objetivo investigar as particularidades dos parâmetros de modelos dinâmicos para populações de plantas daninhas, a partir de um experimento conduzido em campo, usando inferência Bayesiana via método de Monte Carlo com cadeias de Markov e analisar situações que podem alterar a dinâmica do comportamento populacional por meio de simulações.In the agricultural environment, the possibility to predict future events to establish priorities and to plan activities is indispensable for an appropriate management. Mathematical models have become precious tools for the understanding of phenomena and simulation of solutions of a given system for different initial conditions and values of parameters. The growth of plants obeys the certain physiological principles that can be described, in quantitative terms in reply to the environment, through mathematical equations. In agrosystems, the dynamics of weed populations can be described by mathematical models that relates the produced seeds density and seedlings density in areas of a crop. The parameter models can be either directly inferred from experimentation and statistics analysis, or can be extracted from literature. The goals of this work is to investigate the particularitities of the dynamic models parameters for weed populations, from field experiment, using Bayesian inference by Monte Carlo method with Markov chains and to analyze situations that can modify the population behavior by simulations.
21
Racco, Adriana. "Modelos Computacionais para Dinâmica de Populações Reais". Universidade Federal Fluminense, 2003. http://www.bdtd.ndc.uff.br/tde_busca/arquivo.php?codArquivo=267.
Texto completoResumen
Coordenação de Aperfeiçoamento de Pessoal de Nível SuperiorO uso de ferramentas matemáticas, estatísticas e computacionais para estudar o comportamento de sistemas biológicos se faz cada vez mais presente. Este interesse é devido à complexidade apresentada pelas populações, que sofrem influências externas, relativas à interação com o ambiente e influências internas, conseqüências dos interesses conflitantes entre os indivíduos do ecossistema. A nossa proposta é de modelar computacionalmente alguns fenômenos biológicos observados em populações reais, para tentar entender melhor o que está acontecendo e analisar os prováveis efeitos de fatores externos, como os avanços na área de saúde, mudanças no clima ou invasão de nichos por outras espécies. Mostraremos neste trabalho modelos distintos, destacando entre as ferramentas computacionais aplicadas os algoritmos genéticos, que combinam a sobrevivência dos organismos mais adaptados com pequenas mudanças aleatórias nas suas estruturas, e os autômatos celulares, que permitem o estudo da distribuição espacial da população e utilizam regras simples de evolução. Apresentaremos também, uma solução analítica aproximada para um dos problemas estudados. Nos dois primeiros capítulos utilizaremos o modelo Penna para a dinâmica de populações que apresentam estrutura etária, portanto ideal para estudar o envelhecimento de populações, adaptando o modelo à situação a ser estudada. Nos capítulos seguintes iremos propor dois novos modelos para a colonização de substrato por animais marinhos sésseis, onde larvas trazidas de populações distantes competem pela colonização de superfícies submersas, onde se manterão fixos durante toda a vida.
The usefulness of mathematical, statistical and computational tools to study the behavior of biological systems has been affirmed on many opportunities. This interest is mostly due to the complexity presented by the populations that can suffer external influences,for example, due to the interaction with the environment, and internal influences due to the conflicting interests of the individuals of the ecosystem. Our proposal is modelling in a computer, biological phenomena observed in real populations, in order to understand and to analyze the effects of external factors, such as changes on health care and Medicine, changes in the climate or invasion of niches from intruder species. We will work with different models and computational tools such as genetic algorithms, that combine the survival of the fitter organisms with small random changes in its structures; and cellular automata, that allow the study of the space distribution of the population from simple rules for the dynamical evolution. In addition, we also present an analytic solution for one of the studied situations. In the first two chapters we use the so-called Penna model, appropriate to study the aging of populations, for being age structured, by modifying the model according to the situation we will be studying. In the following chapters we propose two new models for the substratum colonization for sessile marine animals, where larvae brought from distant populations compete for the colonization of submerged surfaces, where they will keep fixed during their lifetime.
22
Jonsson, Fredrik. "Physiologically based pharmacokinetic modeling in risk assessment - Development of Bayesian population methods". Doctoral thesis, Solna : National Institute for Working Life (Arbetslivsinstitutet), 2001. http://publications.uu.se/theses/91-7045-599-6/.
Texto completo
23
Lenormand, Maxime. "Initialize and Calibrate a Dynamic Stochastic Microsimulation Model: Application to the SimVillages Model". Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2012. http://tel.archives-ouvertes.fr/tel-00764929.
Texto completoResumen
Le but de cette thèse est de développer des outils statistiques permettant d'initialiser et de calibrer les modèles de microsimulation dynamique stochastique, en partant de l'exemple du modèle SimVillages (développé dans le cadre du projet Européen PRIMA). Ce modèle couple des dynamiques démographiques et économiques appliquées à une population de municipalités rurales. Chaque individu de la population, représenté explicitement dans un ménage au sein d'une commune, travaille éventuellement dans une autre, et possède sa propre trajectoire de vie. Ainsi, le modèle inclut-il des dynamiques de choix de vie, d'étude, de carrière, d'union, de naissance, de divorce, de migration et de décès. Nous avons développé, implémenté et testé les modèles et méthodes suivants: * un modèle permettant de générer une population synthétique à partir de données agrégées, où chaque individu est membre d'un ménage, vit dans une commune et possède un statut au regard de l'emploi. Cette population synthétique est l'état initial du modèle. * un modèle permettant de simuler une table d'origine-destination des déplacements domicile-travail à partir de données agrégées. * un modèle permettant d'estimer le nombre d'emplois dans les services de proximité dans une commune donnée en fonction de son nombre d'habitants et de son voisinage en termes de service. * une méthode de calibration des paramètres inconnus du modèle SimVillages de manière à satisfaire un ensemble de critères d'erreurs définis sur des sources de données hétérogènes. Cette méthode est fondée sur un nouvel algorithme d'échantillonnage séquentiel de type Approximate Bayesian Computation.
24
Thiebaut, Sophie. "Maladies chroniques et pertes d'autonomie chez les personnes âgees : évolutions des dépenses de santé et de la prise en charge de la dépendance sous l'effet du vieillissement de la population". Thesis, Aix-Marseille 2, 2011. http://www.theses.fr/2011AIX24026.
Texto completoResumen
Fondée sur deux analyses empiriques et sur un travail de modélisation théorique, cette thèse traite de la problématique du vieillissement de la population, en France, en termes de dépenses de biens et services de santé, et en termes de prise en charge des personnes âgées dépendantes. Dans un premier chapitre, une méthode de microsimulation dynamique est mise au point afin d'évaluer l'évolution des dépenses de médicaments remboursables (en médecine de ville) sous l'effet du vieillissement de la population et de l'évolution de l'état de santé chronique des personnes âgées. Un deuxième chapitre s'intéresse aux tenants d'une possible réforme de l'Allocation Personnalisée d'Autonomie (APA), qui viserait à récupérer sur la succession une partie des fonds versés aux personnes dépendantes. Nous développons un modèle théorique de transfert intergénérationnel en individualisant les décisions des deux membres d'une famille, un parent dépendant et un enfant aidant informel potentiel. Enfin, dans une dernière partie, nous évaluons empiriquement les facteurs modifiant la demande d'aide à domicile des bénéficiaires de l'APA, en nous concentrant, afin d'anticiper sur de possibles réformes de l'aide publique, sur l'évaluation des effets-prix dans la demande d'aide formelleThis thesis addresses, using an elaborated theoretical model and two empirical applications, issues related to population ageing and health care expenditures as per the French context. In the first chapter, a method of dynamic microsimulation is developed to assess the evolution of outpatient reimbursable drugs expenditures as a result of the ageing population and the evolution of health status of chronically ill elderly people. The second chapter focuses on the ins and outs of a possible reform of the Personal Allowance for Autonomy (APA), which would seek to recover a portion of the funds paid to disabled elderly on the inheritance of their heirs. A theoretical model of intergenerational transfers is developed to study the individual decisions of a two-member family - a disabled parent and a child who can play the role of informal care giver. The final section presents an empirical evaluation of the factors affecting the demand of APA's recipients for home care. This work examines the price effects in the demand for formal care in order to anticipate possible reforms of public allowance
25
Lopes, Marcel Rodrigues. "Estimação de parâmetros de populações de plantas daninhas usando inferência Bayesiana". Universidade de São Paulo, 2007. http://www.teses.usp.br/teses/disponiveis/18/18153/tde-22082007-095725/.
Texto completoResumen
O banco de sementes de plantas daninhas pode vir a ser um sério problema para a atividade agrícola por manter infestações por longos períodos. A dinâmica da população de plantas daninhas pode ser representada por modelos matemáticos que relaciona as densidades de sementes produzidas e de plântulas em áreas de cultivo. Os valores dos parâmetros dos modelos podem ser inferidos diretamente de experimentação e análise estatística. O presente trabalho tem por objetivo estimar parâmetros de populações das plantas daninhas anuais denominadas Digitaria ciliares, Panicum maximum e Euphorbia heterophylla e avaliar um modelo espacial com 2 e 3 parâmetros, a partir de um experimento conduzido em cultura de Zea mays (milho) usando inferência Bayesiana.The seeds bank of weed could be a serious problem to the agricultural activity because it maintains infestations for long periods. The dynamics of weed populations can be described by mathematical models that relates the produced seeds and seedlings densities in areas of crop. The values of the parameters of the models can be inferred from experimentation and statistics analysis. The objective of this work is to estimate parameters of anual weed populations denoted Digitaria ciliares, Panicum maximum e Euphorbia heterophylla and evaluate a spatial model with 2 and 3 parameters from experimental data of Zea mays (corn) fields using Bayesian inference.
26
Tomezak, Maxime. "Radiothérapie du cancer : de la physique de l’ADN irradié à la dormance tumorale". Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL10205/document.
Texto completoResumen
La radiothérapie utilise les radiations dans le but d’éradiquer les cellules cancéreuses, principalement par la génération de cassures double-brin de l’ADN. Un des effets secondaires de la radiothérapie est l’émergence de seconds cancers, préférentiellement en bordure du volume traité, où des cellules normales reçoivent un niveau de dose non létal. Ces seconds sarcomes se développent principalement après une période de latence de 3 à 20 ans. Nous avons déterminé la distribution des dommages à l’ADN (CSB et CDB) dans le champ d’irradiation et en bordure de celui-ci, après différentes conditions d’irradiations. Nous avons évalué les dommages à l’ADN et l’induction de sénescence après un traitement fractionné. La détection des foyers XRCC1 et 53BP1 par immunofluorescence a été utilisé comme marqueurs des CSB et CDB respectivement. Enfin, la sénescence a été évaluée par la mesure de l’activité de l’enzyme SA-beta-galactosidase. Nous avons également développé un modèle théorique d’évolution cellulaire, avec pour objectif le suivi des cellules après l’action d’un traitement géno-toxique, tel que la radiothérapie ou la chimiothérapie. Les caractéristiques principales de cycle cellulaire, d’endommagement et de réparation de l’ADN, et de la diffusion chimique ont été incluses. Le modèle d’évolution cellulaire est basé sur la théorie des chaines de Markov. Deux applications du modèle sont présentées (survie cellulaire et effet bystander)Radiotherapy uses ionizing radiations in order to eradicate cancer cells mainly through the generation of DNA double-strand breaks. A side effect of radiotherapy is the emergence of second cancer, preferentially at the border of the treated volume, where normal cells receive some non-lethal leaking radiations. These second cancers are mainly sarcomas and develop with a latency of 3 to 20 years. We have determine the distribution of DNA damage (SSBs and DSBs) both in-and at the border of the irradiation field following various conditions of irradiation. We also investigated DNA damages and induction of senescence after multi-session of treatment. Fluorescent detection of 53BP1 and XRCC1 foci was used as a marker of DSBs and SSBs respectively. Finally senescence state has been tested by measurement of SA-beta-galactosidase activity. We also developped a theoretical agent-based model of cell evolution under the action of cytotoxic treatments, such as radiotherapy or chemotherapy. The major features of cell cycle and proliferation, cell damage and repair, and chemical diffusion are included. Cell evolution is based on a discrete Markov chain. Two showcase applications of the model are then presented (survival curves and bystander effect)
27
Lenormand, Maxime. "Initialiser et calibrer un modèle de microsimulation dynamique stochastique : application au modèle SimVillages". Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2012. http://tel.archives-ouvertes.fr/tel-00822114.
Texto completoResumen
Le but de cette thèse est de développer des outils statistiques permettant d'initialiser et de calibrer les modèles de microsimulation dynamique stochastique, en partant de l'exemple du modèle SimVillages (développé dans le cadre du projet Européen PRIMA). Ce modèle couple des dynamiques démographiques et économiques appliquées à une population de municipalités rurales. Chaque individu de la population, représenté explicitement dans un ménage au sein d'une commune, travaille éventuellement dans une autre, et possède sa propre trajectoire de vie. Ainsi, le modèle inclut-il des dynamiques de choix de vie, d'étude, de carrière, d'union, de naissance, de divorce, de migration et de décès. Nous avons développé, implémenté et testé les modèles et méthodes suivants : 1 / un modèle permettant de générer une population synthétique à partir de données agrégées, où chaque individu est membre d'un ménage, vit dans une commune et possède un statut au regard de l'emploi. Cette population synthétique est l'état initial du modèle. 2 / un modèle permettant de simuler une table d'origine-destination des déplacements domicile-travail à partir de données agrégées. 3 / un modèle permettant d'estimer le nombre d'emplois dans les services de proximité dans une commune donnée en fonction de son nombre d'habitants et de son voisinage en termes de service. 4 / une méthode de calibration des paramètres inconnus du modèle SimVillages de manière à satisfaire un ensemble de critères d'erreurs définis sur des sources de données hétérogènes. Cette méthode est fondée sur un nouvel algorithme d'échantillonnage séquentiel de type Approximate Bayesian Computation.
28
Abdennur, Nezar A. "A Framework for Individual-based Simulation of Heterogeneous Cell Populations". Thèse, Université d'Ottawa / University of Ottawa, 2011. http://hdl.handle.net/10393/20478.
Texto completoResumen
An object-oriented framework is presented for developing and simulating individual-based models of cell populations. The framework supplies classes to define objects called simulation channels that encapsulate the algorithms that make up a simulation model. These may govern state-updating events at the individual level, perform global state changes, or trigger cell division. Simulation engines control the scheduling and execution of collections of simulation channels, while a simulation manager coordinates the engines according to one of two scheduling protocols. When the ensemble of cells being simulated reaches a specified maximum size, a procedure is introduced whereby random cells are ejected from the simulation and replaced by newborn cells to keep the sample population size constant but representative in composition. The framework permits recording of population snapshot data and/or cell lineage histories. Use of the framework is demonstrated through validation benchmarks and two case studies based on experiments from the literature.
29
Gajda, Dorota. "Optimisation des méthodes algorithmiques en inférence bayésienne. Modélisation dynamique de la transmission d'une infection au sein d'une population hétérogène". Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00659618.
Texto completoResumen
Ce travail se décompose en deux grandes parties, "Estimations répétées dans le cadre de la modélisation bayésienne" et "Modélisation de la transmission de maladies infectieuses dans une population. Estimation des paramètres.". Les techniques développées dans la première partie sont utilisées en fin de la seconde partie. La première partie est consacrée à des optimisations d'algorithmes stochastiques très souvent utilisés, notamment dans le contexte des modélisations Bayésiennes. Cette optimisation est particulièrement faite lors de l'étude empirique d'estimateurs des paramètres d'un modèle où les qualités des estimateurs sont évaluées sur un grand nombre de jeux de données simulées. Quand les lois a posteriori ne sont pas explicites, le recours à des algorithmes stochastiques itératifs (de la famille des algorithmes dits de Monte Carlo par Chaîne de Makov) pour approcher les lois a posteriori est alors très couteux en temps car doit être fait pour chaque jeu de données. Dans ce contexte, ce travail consiste en l'étude de solutions évitant un trop grand nombre d'appels à ces algorithmes mais permettant bien-sûr d'obtenir malgré tout des résultats précis. La principale technique étudiée dans cette partie est celle de l'échantillonnage préférentiel. La seconde partie est consacrée aux études de modèles épidémiques, en particulier le modèle compartimental dit SIS (Susceptible-Infecté-Susceptible) dans sa version stochastique. L'approche stochastique permet de prendre en compte l'hétérogénéité de l'évolution de la maladie dans la population. les approches par des processus Markoviens sont étudiés où la forme des probabilités de passage entre les états est non linéaire. La solution de l'équation différentielle en probabilité n'est alors en général pas explicite. Les principales techniques utilisées dans cette partie sont celles dites de développement de l'équation maîtresse ("master equation") appliquées au modèle SIS avec une taille de population constante. Les propriétés des estimateurs des paramètres sont étudiées dans le cadre fréquentiste et bayésien. Concernant l'approche Bayésienne, les solutions d'optimisation algorithmique de la première partie sont appliquées.
30
Bouaniche, Alexandre. "A hybrid stochastic-sectional method for the simulation of soot particle size distributions Vitiated high karlovitz n-decane/air turbulent flames: scaling laws and micro-mixing modeling analysis A hybrid stochastic/fixed-sectional method for solving the population balance equation". Thesis, Normandie, 2019. http://www.theses.fr/2019NORMIR23.
Texto completoResumen
Les particules de suie (qui sont un type de particules ultrafines) peuvent être produites et émises dans des conditions de combustion riche. Les secteurs comme les transports (routier et aérien), où l'industrie sont des contributeurs significatifs aux émissions de particules. Celles-ci sont habituellement considérées comme des polluants dans la mesure où leur impact négatif sur la santé a été mesuré. Dans certains cas spécifiques comme la production de nanomatériaux, elles peuvent être synthétisées de manière volontaire. Dans les deux cas, une compréhension précise et une capabilité de prédiction de la distribution de tailles de particules (PSD en anglais) sont nécessaires, pour une meilleure conception des chambres de combustion. Dans cette thèse, une méthode innovante est proposée pour la prédiction de l'évolution de la distribution de tailles de particules (PSD). Elle consiste en une approche hybride composée de particules stochastiques représentant une fonction de densité de probabilité (PDF en anglais) et de sections fixes. L'objectif est de résoudre de manière précise le terme source de croissance/oxydation, en traitant le problème de diffusion numérique rencontré par des méthodes sectionnelles classiques. D'autre part, la méthode proposée est moins coûteuse qu'une méthode de Monte Carlo complète. D'abord, le contexte et les motivations de cette thèse sont expliqués. Les concepts et modèles pour les termes sources physiques de suie sont brièvement résumés. Ensuite, l'équation de bilan de population (PBE en anglais) qui pilote l'évolution de la distribution de tailles de particules (PSD), est présentée, ainsi que les différentes classes de méthodes utilisées pour sa résolution. La nouvelle méthode hybride est introduite. Sa précision et son efficacité sont démontrées sur des cas tests analytiques. Enfin, la méthode est appliquée sur une flamme prémélangée d'éthylèneSoot particles (which are one kind of ultra-fine particles) can be produced and emitted in fuel rich combustion conditions. Sectors like road and air transportation, or industry are significant contributors to soot particles emissions. Soot particles are usually considered as a pollutant as their negative impact on health has been assessed. In some specific cases like nanomaterials production, they can be synthesized on purpose. In both cases, accurate understanding and prediction capability of the Particle Size Distribution (PSD) is needed, for a better combustors design. In this thesis, a novel numerical method is proposed to predict the Particle Size Distribution (PSD) evolution. It consists in a hybrid approach featuring stochastic particles representing a Probability Density Function (PDF), and fixed sections. The objective is to solve accurately for the surface growth/oxidation term, mitigating the problem of numerical diffusion encountered in some classical sectional methods. On the other hand, the proposed method is less expensive than a full Monte Carlo method. First, the context and motivation of the thesis are explained. Concepts and models for soot physical source terms are shortly reviewed. Then, the Population Balance Equation (PBE), which drives the evolution of the Particle Size Distribution (PSD), is presented as well as the different classes of numerical methods used for its resolution. Subsequently, the novel hybrid method is introduced. Its accuracy and efficiency are demonstrated on analytical test cases. Finally, the method is applied on a premixed ethylene sooting flame
31
Ujamaa, Dawud A. "Assessing the Effect of Prior Distribution Assumption on the Variance Parameters in Evaluating Bioequivalence Trials". Digital Archive @ GSU, 2006. http://digitalarchive.gsu.edu/math_theses/13.
Texto completoResumen
Bioequivalence determines if two drugs are alike. The three kinds of bioequivalence are Average, Population, and Individual Bioequivalence. These Bioequivalence criteria can be evaluated using aggregate and disaggregate methods. Considerable work assessing bioequivalence in a frequentist method exists, but the advantages of Bayesian methods for Bioequivalence have been recently explored. Variance parameters are essential to any of theses existing Bayesian Bioequivalence metrics. Usually, the prior distributions for model parameters use either informative priors or vague priors. The Bioequivalence inference may be sensitive to the prior distribution on the variances. Recently, there have been questions about the routine use of inverse gamma priors for variance parameters. In this paper we examine the effect that changing the prior distribution of the variance parameters has on Bayesian models for assessing Bioequivalence and the carry-over effect. We explore our method with some real data sets from the FDA.
32
Abeyratne, Anura T. "Comparison of k-Weibull populations under random censoring /". free to MU campus, to others for purchase, 1996. http://wwwlib.umi.com/cr/mo/fullcit?p9737910.
Texto completo
33
Magued, Michael. "Virtualisation de la mesure d’exposition du public général au champ magnétique basse fréquence dans le domaine de l’automobile". Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC015/document.
Texto completoResumen
L’exposition des personnes aux champs électromagnétiques est une problématique majeure de société qui touche le domaine de l’automobile. Le développement de la technologie des véhicules électriques et hybrides nécessite la prise en compte de la problématique d’exposition aux ondes dès la phase même de la conception.Le travail présenté dans ce document s’intéresse principalement à l’exposition aux champs magnétiques basse fréquence (BF) marqués par les effets non thermiques de stimulation électriques. Dans cette gamme fréquentielle, les sources principales des risques d’exposition sont les modules de la chaîne de traction qui sont souvent situés à proximité des passagers. L’objectif principal de cette thèse est de virtualiser la mesure évaluant l’exposition aux champs magnétiques BF, jusqu’ici réalisée par un testeur de niveau d’exposition commercial, afin d’être capable de faire une levée de risque d’exposition, en amont, sans entraîner de surcoût au constructeur. Ceci est réalisé en virtualisant l’instrument de mesure.Nous consacrons d’abord notre étude à la compréhension de la mesure d’évaluation d’exposition et du fonctionnement du champmètre Narda ELT-400 utilisé chez notre constructeur automobile pour mesurer l’indice d’exposition. Ainsi, nous détaillons les différentes définitions et méthodes de calcul de l’indice d’exposition du public général aux champs magnétiques BF. Enfin, nous présentons des applications de l’utilisation du champmètre sur des cas de mesure en statique et en dynamique.La deuxième partie de l’étude traite de la construction du prototype virtuel permettant de modéliser la mesure d’indice d’exposition aux champs magnétiques BF réalisée par le champmètre Narda ELT-400. Pour ce faire, nous développons et optimisons dans un premier temps le modèle de la sonde triaxiale du champmètre sous FEKO permettant de positionner et d’orienter la sonde selon le choix de l’utilisateur. Ensuite le champ magnétique rayonné par la sonde virtuelle est traité pour obtenir une mesure virtuelle de l’induction magnétique détectée par la sonde et de l’indice d’exposition.La troisième partie est consacrée à la validation du modèle complet sur des cas réels de mesures effectuées sur des pinces manuelles de soudage par points en comparant les résultats du prototype virtuel à ceux mesurés. La validation du modèle est réalisée dans trois cas d’étude différents correspondant à des profils de champ différents, des fréquences différentes dans la gamme BF et à des formes de signal différentes.Dans la dernière partie de notre étude, une approche stochastique de simulation est proposée en appliquant la méthode de Monte-Carlo, basée sur un grand nombre de tirages aléatoires. Cette méthode permet d’étudier la dispersion des résultats due à l’imprécision plausible de positionnement et d’orientation commise par l’opérateur de la sonde. Cette méthode est appliquée à différentes distances de sources rayonnantes élémentaires. Les résultats principaux de cette partie portent sur le lien entre l’homogénéité du champ au point investigué et la variabilité de la mesure virtuelle autour de ce point suite à l’imprécision commiseExposure to electromagnetic fields is a major issue in society that affects the automotive domain. The development of electric and hybrid vehicles technology requires the consideration of the issue of exposure since the conception stage.The work presented in this paper is mainly concerned with exposure to low-frequency (LF) magnetic fields distinguished with non-thermal electric stimulation effects. In this frequency range, the main sources of exposure risks are the powertrain elements often located close to the passengers.The main objective of this thesis is to virtualize the measurement assessing exposure to LF magnetic fields, hitherto performed by a commercial exposure level tester, to be able to minimize exposure risks, a priori, without incurring additional costs to the manufacturer. This is realized by virtualizing the measuring instrument.We focus first on understanding the exposure evaluation measurement and on the operation of the ELT-400 Narda field meter used at our automobile manufacturer to measure the exposure index. Thus, we show the different definitions and methods of calculating exposure index of the general public to LF magnetic fields. Finally, we present applications of the use of the field meter on measuring cases in statistic and dynamic states.The second part of the study is consecrated to the construction of the virtual prototype to model the measurement of the exposure index to LF magnetic fields performed by Narda field meter ELT-400. To do this, first we develop and optimize the model of the field meter’s triaxial probe in FEKO to position and orient the probe as selected by the user. Then the magnetic field radiated by the virtual probe is processed to obtain a virtual measurement of the magnetic induction detected by the probe and of the exposure index.The third part of the study deals with the validation of the whole model on real cases of measurements done over manual spot welding clamps by comparing the virtual prototype results with those measured. The model validation is performed in three different case studies corresponding to different field profiles, different frequencies in LF domain and different forms of signal.In the last part of our study, a stochastic simulation approach is proposed by applying the Monte-Carlo Method based on a large number of random draws. This method allows studying the dispersion of results due to the plausible imprecise positioning and orientation committed by the operator of the probe. This method is applied at different distances from elementary radiating sources. The main results of this part focus on the link between the field homogeneity at the investigated point and the variability of the virtual measurement around this point due to the inaccuracy committed
34
Guerillot, Françoise. "Bases biométriques de l'estimation de la sensibilité bactérienne aux antibiotiques ou une heuristique de la comparaison des dynamiques de populations bactériennes". Lyon 1, 1994. http://www.theses.fr/1994LYO10137.
Texto completoResumen
La determination de la sensibilite bacterienne aux antibiotiques est primordiale pour orienter une therapeutique. Notre travail consiste a preciser sur quels arguments les etudes de dynamiques de populations bacteriennes en presence d'antibiotiques peuvent conduire a definir la sensibilite bacterienne. La croissance bacterienne est suivie par une mesure sequentielle turbidimetrique toutes les 5 minutes. Une typologie des courbes de croissance par classification automatique montre que les modes de croissance dans un milieu donne sont independants de l'espece bacterienne et specifique d'une souche. Toute modification de croissance induite par un antibiotique est evaluee en comparant la courbe de croissance en presence d'antibiotique et la courbe de croissance temoin, sans antibiotique. Les vitesses de croissance sont estimees apres lissage des donnees par une fonction spline. L'ecart entre deux courbes de croissance est quantifie en evaluant le coefficient de regression orthogonale entre les vitesses de croissance. Les intervalles de confiance des coefficients de regression sont determines par une methode bootstrap. Il est alors possible d'interpreter les resultats a l'aide d'un test statistique simple. Une concentration minimale d'antibiotique qui induit une variation significative de la croissance est ainsi determinee dans le cas des antibiotiques qui modifient le taux de croissance. La mortalite bacterienne qui s'inscrit dans le cadre d'une determination precoce de la sensibilite bacterienne est egalement etudiee. L'utilisation des parametres d'un modele descriptif ajuste aux donnees cinetiques de mortalite parait inadaptee a la comparaison des effets bactericides. Nous mesurons l'effet bactericide apres un temps de traitement antibacterien par la probabilite de survie. La determination des intervalles de confiance sur ces mesures grace a des methodes de simulation permet de definir un test de comparaison des effets bactericides. Cette methode est appliquee a l'etude des associations d'antibiotiques. La notion de probabilite de survie permet ainsi de definir de facon rigoureuse les effets des associations
35
Mignon, Charles. "Photo-biomodulation of human skin fibroblast sub-populations : a systematic approach for the optimization of optical treatment parameters". Thesis, University of Bradford, 2017. http://hdl.handle.net/10454/16064.
Texto completoResumen
The thesis presents a rational path for the optimization of the selection of optical treatment parameters in photobiomodulation of human skin fibroblasts. The project begins with an extensive analysis of 90 bibliographic reports in photobiomodulation published between 1985 and 2015, and revealed major inconsistencies in optical parameters selected for clinical applications. Seeking greater clarity for optimal parameter choice, a systematic approach to disentangle the multiple factors underpinning the response of human dermal fibroblasts in vitro to visible and near-infra red (NIR) light was employed. Light-based devices were constructed to specifically and systematically screen the optical parameter window (i.e. wavelength, irradiance and dose) observed in literature. Additionally, critical culture and treatment conditions that have dramatic impact on the outcome of specific light treatment of these human skin dermal cells were identified. In particular, environmental oxygen concentration, cell confluency and serum concentration were all found to have a great effect on the response of dermal fibroblasts to light. In parallel, the induction of reactive oxygen species (ROS) by short visible wavelengths on two dermal fibroblast sub-populations or lineage, reticular and papillary, was monitored by live-cell imaging. The ROS species were found to be created in or close to mitochondria. Lastly, gene expression studies revealed a strong impact of short visible wavelengths, as compared to long and NIR wavelengths on both subpopulations of human dermal fibroblasts. In particular, blue light (450 nm) specifically down-regulated proliferation, metabolism and protein synthesis molecular pathways. At the protein level, 450-nm light inhibited the production of procollagen I in human reticular and papillary fibroblasts in a dose-dependent manner. Gene expression results were in agreement i.e., the same light parameter down-regulated collagen fiber genes, integrins and up-regulated collagenase MMP1. This thesis concludes with a chapter presenting a characterization of the accuracy of a potential translation tool for the prediction of optical photon density inside human skin.
36
Delescluse, Matthieu. "Une approche Monte Carlo par Chaînes de Markov pour la classification des potentiels d'action. Application à l'étude des corrélations d'activité des cellules de Purkinje". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2005. http://tel.archives-ouvertes.fr/tel-00011123.
Texto completoResumen
Pour être réellement exploitables, les données d'enregistrements extracellulaires multiunitaires doivent faire l'objet d'un traitement préalable visant à isoler les activités neuronales individuelles qui les constituent: le spike-sorting. Ce travail de thèse est une contribution au développement et à la réalisation d'une méthode automatique de spike-sorting implémentant un algorithme de Monte Carlo par Chaînes de Markov (MCMC). La méthode proposée permet de tenir compte, en plus de la forme des potentiels d'action (PAs), de l'information fournie par leurs temps d'émission pour réaliser la classification. Cette utilisation de l'information temporelle rend possible l'identification automatique de neurones émettant des PAs de formes non stationnaires. Elle améliore aussi grandement la séparation de neurones aux PAs de formes similaires. Ce travail méthodologique à débouché sur la création d'un logiciel libre accompagné de son manuel d'utilisateur.Cette méthode de spike-sorting a fait l'objet d'une validation expérimentale sur des populations de cellules de Purkinje (PCs), dans les tranches de cervelet de rat. Par ailleurs, l'étude des trains de PAs de ces cellules fournis par le spike-sorting, n'a pas révélé de corrélations temporelles significatives en régime spontané, en dépit de l'existence d'une inhibition commune par les interneurones de la couche moléculaire et d'une inhibition directe de PC à PC. Des simulations ont montré que l'influence de ces inhibitions sur les relations temporelles entre les trains de PCs était trop faible pour pouvoir être détectée par nos méthodes d'analyse de corrélations. Les codes élaborés pour l'analyse des trains de PAs sont également disponibles sous la forme d'un second logiciel libre.
37
Delescluse, Matthieu. "Une approche Monte Carlo par chaînes de Markov pour la classification des potentiels d' action : application à l' étude des corrélations d' activité des cellules de Purkinje". Paris 6, 2005. http://www.theses.fr/2005PA066493.
Texto completo
38
Wang, Xiaoyin. "Bayesian analysis of capture-recapture models /". free to MU campus, to others for purchase, 2002. http://wwwlib.umi.com/cr/mo/fullcit?p3060157.
Texto completo
39
Wang, Rui. "Generalizing Multistage Partition Procedures for Two-parameter Exponential Populations". ScholarWorks@UNO, 2018. https://scholarworks.uno.edu/td/2510.
Texto completoResumen
ANOVA analysis is a classic tool for multiple comparisons and has been widely used in numerous disciplines due to its simplicity and convenience. The ANOVA procedure is designed to test if a number of different populations are all different. This is followed by usual multiple comparison tests to rank the populations. However, the probability of selecting the best population via ANOVA procedure does not guarantee the probability to be larger than some desired prespecified level. This lack of desirability of the ANOVA procedure was overcome by researchers in early 1950's by designing experiments with the goal of selecting the best population. In this dissertation, a single-stage procedure is introduced to partition k treatments into "good" and "bad" groups with respect to a control population assuming some key parameters are known. Next, the proposed partition procedure is genaralized for the case when the parameters are unknown and a purely-sequential procedure and a two-stage procedure are derived. Theoretical asymptotic properties, such as first order and second order properties, of the proposed procedures are derived to document the efficiency of the proposed procedures. These theoretical properties are studied via Monte Carlo simulations to document the performance of the procedures for small and moderate sample sizes.
40
Sedki, Mohammed. "Échantillonnage préférentiel adaptatif et méthodes bayésiennes approchées appliquées à la génétique des populations". Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2012. http://tel.archives-ouvertes.fr/tel-00769095.
Texto completoResumen
Cette thèse propose et étudie deux techniques d'inférence bayésienne dans les modèles où la vraisemblance possède une composante latente. Dans ce contexte, la vraisemblance d'un jeu de données observé est l'intégrale de la vraisemblance dite complète sur l'espace de la variable latente. On s'intéresse aux cas où l'espace de la variable latente est de très grande dimension et comporte des directions de différentes natures (discrètes et continues), ce qui rend cette intégrale incalculable. Le champs d'application privilégié de cette thèse est l'inférence dans les modèles de génétique des populations. Pour mener leurs études, les généticiens des populations se basent sur l'information génétique extraite des populations du présent et représente la variable observée. L'information incluant l'histoire spatiale et temporelle de l'espèce considérée est inaccessible en général et représente la composante latente. Notre première contribution dans cette thèse suppose que la vraisemblance peut être évaluée via une approximation numériquement coûteuse. Le schéma d'échantillonnage préférentiel adaptatif et multiple (AMIS pour Adaptive Multiple Importance Sampling) de Cornuet et al. nécessite peu d'appels au calcul de la vraisemblance et recycle ces évaluations. Cet algorithme approche la loi a posteriori par un système de particules pondérées. Cette technique est conçue pour pouvoir recycler les simulations obtenues par le processus itératif (la construction séquentielle d'une suite de lois d'importance). Dans les nombreux tests numériques effectués sur des modèles de génétique des populations, l'algorithme AMIS a montré des performances numériques très prometteuses en terme de stabilité. Ces propriétés numériques sont particulièrement adéquates pour notre contexte. Toutefois, la question de la convergence des estimateurs obtenus par cette technique reste largement ouverte. Dans cette thèse, nous montrons des résultats de convergence d'une version légèrement modifiée de cet algorithme. Sur des simulations, nous montrons que ses qualités numériques sont identiques à celles du schéma original. Dans la deuxième contribution de cette thèse, on renonce à l'approximation de la vraisemblance et on supposera seulement que la simulation suivant le modèle (suivant la vraisemblance) est possible. Notre apport est un algorithme ABC séquentiel (Approximate Bayesian Computation). Sur les modèles de la génétique des populations, cette méthode peut se révéler lente lorsqu'on vise une approximation précise de la loi a posteriori. L'algorithme que nous proposons est une amélioration de l'algorithme ABC-SMC de Del Moral et al. que nous optimisons en nombre d'appels aux simulations suivant la vraisemblance, et que nous munissons d'un mécanisme de choix de niveaux d'acceptations auto-calibré. Nous implémentons notre algorithme pour inférer les paramètres d'un scénario évolutif réel et complexe de génétique des populations. Nous montrons que pour la même qualité d'approximation, notre algorithme nécessite deux fois moins de simula- tions par rapport à la méthode ABC avec acceptation couramment utilisée.
41
Calmet, Claire. "Inférences sur l'histoire des populations à partir de leur diversité génétique : étude de séquences démographiques de type fondation-explosion". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2002. http://tel.archives-ouvertes.fr/tel-00288526.
Texto completoResumen
L'étude de la démographie dans une perspective historique participe à la compréhension des processus évolutifs. Les données de diversité génétique sont potentiellement informatives quant au passé démographique des populations: en effet, ce passé est enregistré avec perte d'information par les marqueurs moléculaires, par l'intermédiaire de leur histoire généalogique et mutationnelle. L'acquisition de données de diversité génétique est de plus en plus rapide et aisée, et concerne potentiellement n'importe quel organisme d'intérêt. D'où un effort dans la dernière décennie pour développer les outils statistiques permettant d'extraire l'information démographique des données de typage génétique.La présente thèse propose une extension de la méthode d'inférence bayésienne développée en 1999 par M. Beaumont. Comme la méthode originale, (i) elle est basée sur le coalescent de Kingman avec variations d'effectif, (ii) elle utilise l'algorithme de Metropolis-Hastings pour échantillonner selon la loi a posteriori des paramètres d'intérêt et (iii) elle permet de traiter des données de typage à un ou plusieurs microsatellites indépendants. La version étendue généralise les modèles démographique et mutationnel supposés dans la méthode initiale: elle permet d'inférer les paramètres d'un modèle de fondation-explosion pour la population échantillonnée et d'un modèle mutationnel à deux phases, pour les marqueurs microsatellites typés. C'est la première fois qu'une méthode probabiliste exacte incorpore pour les microsatellites un modèle mutationnel autorisant des sauts.
Le modèle démographique et mutationnel est exploré. L'analyse de jeux de données simulés permet d'illustrer et de comparer la loi a posteriori des paramètres pour des scénarios historiques: par exemple une stabilité démographique, une croissance exponentielle et une fondation-explosion. Une typologie des lois a posteriori est proposée. Des recommandations sur l'effort de typage dans les études empiriques sont données: un unique marqueur microsatellite peut conduire à une loi a posteriori très structurée. Toutefois, les zones de forte densité a posteriori représentent des scénarios de différents types. 50 génomes haploides typés à 5 marqueurs microsatellites suffisent en revanche à détecter avec certitude (99% de la probabilité a posteriori) une histoire de fondation-explosion tranchée. Les conséquences de la violation des hypothèses du modèle démographique sont discutées, ainsi que les interactions entre processus et modèle mutationnel. En particulier, il est établi que le fait de supposer un processus mutationnel conforme au modèle SMM, alors que ce processus est de type TPM, peut générer un faux signal de déséquilibre génétique. La modélisation des sauts mutationnels permet de supprimer ce faux signal.
La méthode est succinctement appliquée à l'étude de deux histoires de fondation-explosion: l'introduction du chat Felis catus sur les îles Kerguelen et celle du surmulot Rattus norvegicus sur les îles du large de la Bretagne. Il est d'abord montré que la méthode fréquentiste développée par Cornuet et Luikart (1996) ne permet pas de détecter les fondations récentes et drastiques qu'ont connu ces populations. Cela est vraisemblablement dû à des effets contraires de la fondation et de l'explosion, sur les statistiques utilisées dans cette méthode.
La méthode bayésienne ne détecte pas non plus la fondation si l'on force une histoire démographique en marche d'escalier, pour la même raison. La fondation et l'explosion deviennent détectables si le modèle démographique les autorise. Toutefois, les dépendances entre les paramètres du modèle empêchent de les inférer marginalement avec précision. Toute information a priori sur un paramètre contraint fortement les valeurs des autres paramètres. Ce constat confirme le potentiel de populations d'histoire documentée pour l'estimation indirecte des paramètres d'un modèle de mutation des marqueurs.
42
Low, Choy Samantha Jane. "Hierarchical models for 2D presence/absence data having ambiguous zeroes: With a biogeographical case study on dingo behaviour". Thesis, Queensland University of Technology, 2001. https://eprints.qut.edu.au/37098/12/Samantha%20Low%20Choy%20Thesis.pdf.
Texto completoResumen
This dissertation is primarily an applied statistical modelling investigation, motivated by a case study comprising real data and real questions. Theoretical questions on modelling and computation of normalization constants arose from pursuit of these data analytic questions.
The essence of the thesis can be described as follows.
Consider binary data observed on a two-dimensional lattice. A common problem with such data is the ambiguity of zeroes recorded. These may represent zero response given some threshold (presence) or that the threshold has not been triggered (absence). Suppose that the researcher wishes to estimate the effects of covariates on the binary responses, whilst taking into account underlying spatial variation, which is itself of some interest. This situation arises in many contexts and the dingo, cypress and toad case studies described in the motivation chapter are examples of this.
Two main approaches to modelling and inference are investigated in this thesis.
The first is frequentist and based on generalized linear models, with spatial variation modelled by using a block structure or by smoothing the residuals spatially. The EM algorithm can be used to obtain point estimates, coupled with bootstrapping or asymptotic MLE estimates for standard errors.
The second approach is Bayesian and based on a three- or four-tier hierarchical model, comprising a logistic regression with covariates for the data layer, a binary Markov Random field (MRF) for the underlying spatial process, and suitable priors for parameters in these main models. The three-parameter autologistic model is a particular MRF of interest. Markov chain Monte Carlo (MCMC) methods comprising hybrid Metropolis/Gibbs samplers is suitable for computation in this situation. Model performance can be gauged by MCMC diagnostics.
Model choice can be assessed by incorporating another tier in the modelling hierarchy. This requires evaluation of a normalization constant, a notoriously difficult problem. Difficulty with estimating the normalization constant for the MRF can be overcome by using a path integral approach, although this is a highly computationally intensive method.
Different methods of estimating ratios of normalization constants (N Cs) are investigated, including importance sampling Monte Carlo (ISMC), dependent Monte Carlo based on MCMC simulations (MCMC), and reverse logistic regression (RLR). I develop an idea present though not fully developed in the literature, and propose the Integrated mean canonical statistic (IMCS) method for estimating log NC ratios for binary MRFs. The IMCS method falls within the framework of the newly identified path sampling methods of Gelman & Meng (1998) and outperforms ISMC, MCMC and RLR. It also does not rely on simplifying assumptions, such as ignoring spatio-temporal dependence in the process. A thorough investigation is made of the application of IMCS to the three-parameter Autologistic model. This work introduces background computations required for the full implementation of the four-tier model in Chapter 7.
Two different extensions of the three-tier model to a four-tier version are investigated. The first extension incorporates temporal dependence in the underlying spatio-temporal process. The second extensions allows the successes and failures in the data layer to depend on time. The MCMC computational method is extended to incorporate the extra layer. A major contribution of the thesis is the development of a fully Bayesian approach to inference for these hierarchical models for the first time.
Note: The author of this thesis has agreed to make it open access but invites people downloading the thesis to send her an email via the 'Contact Author' function.
43
Mutsvairo, Itayi. "Bootstrap interval estimation of wildlife population sizes from multiple surveys". Thesis, 2008. http://hdl.handle.net/10539/4864.
Texto completoResumen
The research deals with bootstrap interval estimation of wildlife population sizes from
multiple surveys in the Hluhluwe-Umfolosi Park. The jackknife procedure was also used
to provide the standard errors for the survey estimates. The main wildlife speciese studied
in the research were the White and Black Rhino. The survey estimates for the wildlife
species were obtained using line transect sampling and mark-recapture methods
respectively. The bootstrap and jackknife procedures were applied separately to each of
the datasets. Bootstrap estimates for each of the time point were obtained and the
confidence intervals of the bootstrap estimates were constructed using percentile and
standard methods. The coverage probability was assessed using the Monte Carlo
simulations. Only the nonparametric bootstrap was applied in this research and the results
were compared to the jackknife results. The lengths of the confidence intervals were used
to assess the confidence intervals with a shorter confidence interval being more exact.
The estimates used for both the bootstrap and jackknife methodology were based on a
simple state space model. The discrete state space model used was proposed by Fatti et al
(2002). State space models provide a natural framework for estimating and predicting
animal population abundance given partial or inexact information. The model takes into
account the (unknown) birth rate in the population and all known losses (mortalities and
relocations) and gains (introductions) in the population between successive surveys as
well as the errors in the survey estimates.
44
Carvalho, Leonel de Magalhães. "Advances on the Sequential Monte Carlo Reliability Assessment of Generation-Transmission Systems using Cross-Entropy and Population-based Methods". Doctoral thesis, 2013. https://repositorio-aberto.up.pt/handle/10216/72688.
Texto completo
45
Carvalho, Leonel de Magalhães. "Advances on the Sequential Monte Carlo Reliability Assessment of Generation-Transmission Systems using Cross-Entropy and Population-based Methods". Tese, 2013. https://repositorio-aberto.up.pt/handle/10216/72688.
Texto completo
46
Wu, Mingqi. "Population SAMC, ChIP-chip Data Analysis and Beyond". 2010. http://hdl.handle.net/1969.1/ETD-TAMU-2010-12-8752.
Texto completoResumen
This dissertation research consists of two topics, population stochastics approximation Monte Carlo (Pop-SAMC) for Baysian model selection problems and ChIP-chip data analysis. The following two paragraphs give a brief introduction to each of the two topics, respectively.
Although the reversible jump MCMC (RJMCMC) has the ability to traverse the space of possible models in Bayesian model selection problems, it is prone to becoming trapped into local mode, when the model space is complex. SAMC, proposed by Liang, Liu and Carroll, essentially overcomes the difficulty in dimension-jumping moves, by introducing a self-adjusting mechanism. However, this learning mechanism has not yet reached its maximum efficiency. In this dissertation, we propose a Pop-SAMC algorithm; it works on population chains of SAMC, which can provide a more efficient self-adjusting mechanism and make use of crossover operator from genetic algorithms to further increase its efficiency. Under mild conditions, the convergence of this algorithm is proved. The effectiveness of Pop-SAMC in Bayesian model selection problems is examined through a change-point identification example and a large-p linear regression variable selection example. The numerical results indicate that Pop- SAMC outperforms both the single chain SAMC and RJMCMC significantly.
In the ChIP-chip data analysis study, we developed two methodologies to identify the transcription factor binding sites: Bayesian latent model and population-based
test. The former models the neighboring dependence of probes by introducing a latent indicator vector; The later provides a nonparametric method for evaluation of test scores in a multiple hypothesis test by making use of population information of samples. Both methods are applied to real and simulated datasets. The numerical results indicate the Bayesian latent model can outperform the existing methods, especially when the data contain outliers, and the use of population information can significantly improve the power of multiple hypothesis tests.
47
Peyret, Thomas. "Évaluation de la variabilité interindividuelle de la toxicocinétique de composés organiques volatils chez l'humain". Thèse, 2007. http://hdl.handle.net/1866/7564.
Texto completo
48
Nong, Andy. "Caractérisation de la variabilité interindividuelle de la toxicocinétique des composés organiques volatils". Thèse, 2006. http://hdl.handle.net/1866/17769.
Texto completo
49
Chung, Yu-Wei y 莊昱偉. "Monte Carlo Sampling of Sequential Likelihood Procedure for Selecting a Subset of Size s which are contained in the Best t (t>=s) populations". Thesis, 1995. http://ndltd.ncl.edu.tw/handle/09111651118401105662.
Texto completoResumen
碩士淡江大學
數學系
83
In many of the experimental situations, one is faced with the problems, e.g. drug efficiency, crop yields, etc, of selecting the better ones from a given collection. Bechhofer (1954) developed a procedure based on predetermined number of observations from normal population's with unknown mean and known variance. Mahamunulu(1967) considered a fixed-sample procedure of selecting a subset of size s which contains at least c of the t best populations.(max(1,s+t+1-k)=