Дисертації з теми "Rééchantillonage"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-31 дисертацій для дослідження на тему "Rééchantillonage".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Arlot, Sylvain. "Rééchantillonnage et Sélection de modèles." Phd thesis, Université Paris Sud - Paris XI, 2007. http://tel.archives-ouvertes.fr/tel-00198803.
Повний текст джерелаLa majeure partie de ce travail de thèse consiste dans la calibration précise de méthodes de sélection de modèles optimales en pratique, pour le problème de la prédiction. Nous étudions la validation croisée V-fold (très couramment utilisée, mais mal comprise en théorie, notamment pour ce qui est de choisir V) et plusieurs méthodes de pénalisation. Nous proposons des méthodes de calibration précise de pénalités, aussi bien pour ce qui est de leur forme générale que des constantes multiplicatives. L'utilisation du rééchantillonnage permet de résoudre des problèmes difficiles, notamment celui de la régression avec un niveau de bruit variable. Nous validons théoriquement ces méthodes du point de vue non-asymptotique, en prouvant des inégalités oracle et des propriétés d'adaptation. Ces résultats reposent entre autres sur des inégalités de concentration.
Un second problème que nous abordons est celui des régions de confiance et des tests multiples, lorsque l'on dispose d'observations de grande dimension, présentant des corrélations générales et inconnues. L'utilisation de méthodes de rééchantillonnage permet de s'affranchir du fléau de la dimension, et d'"apprendre" ces corrélations. Nous proposons principalement deux méthodes, et prouvons pour chacune un contrôle non-asymptotique de leur niveau.
Lesquoy-de, Turckheim Élisabeth. "Tests non paramétriques et rééchantillonnage : le modèle de Cox périodique." Paris 11, 1987. http://www.theses.fr/1987PA112474.
Повний текст джерелаThe first part proposes two nonparametric test defined by a simulation. One compares two distributions functions in a two-by-two black design, the other tests the independence of two censored survival times. The second part is an adaptation of Cox's regression model to a counting process having a periodic underlying intensity and predictable processes as regressors. These processes are ergodic and ϕ-mixing. The underlying intensity is estimated using either an empirical distribution-type estimate or a histogram-type estimate. These two estimates are asymptotically Gaussian and equivalent, as well as the associated regression parameters estimates. Finally, the model is applied to the analysis of a feeding pattern. The third part is a. Modelling of the kinetics of drought rhizogenesis of Sinapis alba
Lerasle, Matthieu. "Rééchantillonnage et sélection de modèles optimale pour l'estimation de la densité." Toulouse, INSA, 2009. http://eprint.insa-toulouse.fr/archive/00000290/.
Повний текст джерелаAhmed, Mohamed Hafez Soliman. "Statistiques réduisant le biais et modèles de rééchantillonnage complet et incomplet." Paris 6, 1986. http://www.theses.fr/1986PA066442.
Повний текст джерелаFerfache, Anouar Abdeldjaoued. "Les M-estimateurs semiparamétriques et leurs applications pour les problèmes de ruptures." Thesis, Compiègne, 2021. http://www.theses.fr/2021COMP2643.
Повний текст джерелаIn this dissertation we are concerned with semiparametric models. These models have success and impact in mathematical statistics due to their excellent scientific utility and intriguing theoretical complexity. In the first part of the thesis, we consider the problem of the estimation of a parameter θ, in Banach spaces, maximizing some criterion function which depends on an unknown nuisance parameter h, possibly infinite-dimensional. We show that the m out of n bootstrap, in a general setting, is weakly consistent under conditions similar to those required for weak convergence of the non smooth M-estimators. In this framework, delicate mathematical derivations will be required to cope with estimators of the nuisance parameters inside non-smooth criterion functions. We then investigate an exchangeable weighted bootstrap for function-valued estimators defined as a zero point of a function-valued random criterion function. The main ingredient is the use of a differential identity that applies when the random criterion function is linear in terms of the empirical measure. A large number of bootstrap resampling schemes emerge as special cases of our settings. Examples of applications from the literature are given to illustrate the generality and the usefulness of our results. The second part of the thesis is devoted to the statistical models with multiple change-points. The main purpose of this part is to investigate the asymptotic properties of semiparametric M-estimators with non-smooth criterion functions of the parameters of multiple change-points model for a general class of models in which the form of the distribution can change from segment to segment and in which, possibly, there are parameters that are common to all segments. Consistency of the semiparametric M-estimators of the change-points is established and the rate of convergence is determined. The asymptotic normality of the semiparametric M-estimators of the parameters of the within-segment distributions is established under quite general conditions. We finally extend our study to the censored data framework. We investigate the performance of our methodologies for small samples through simulation studies
Goldfarb, Bernard. "Etude structurelle des séries temporelles : les moyens de l'analyse spectrale." Paris 9, 1997. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1997PA090007.
Повний текст джерелаZinger, Svitlana. "Interpolation et rééchantillonnage de données spatiales et application à la cartographie urbaine et à la détermination du fond cosmique primordial." Phd thesis, Télécom ParisTech, 2004. http://pastel.archives-ouvertes.fr/pastel-00000944.
Повний текст джерелаCelisse, Alain. "Model selection via cross-validation in density estimation, regression, and change-points detection." Paris 11, 2008. http://www.theses.fr/2008PA112221.
Повний текст джерелаIn this thesis, we aim at studying a family of resampling algorithms, referred to as cross-validation, and especially of one of them named leave-p-out. Extensively used in practice, these algorithms remain poorly understood, especially in the non-asymptotic framework. Our analysis of the leave-p-out algorithm is carried out both in density estimation and regression. Its main concern is to better understand cross-validation with respect to the cardinality p of the test set. From a general point of view, cross-validation is devoted to estimate the risk of an estimator. Usually due to a prohibitive computational complexity, the leave-p-out is intractable. However, we turned it into a feasible procedure thanks to closed-form formulas for the risk estimator of a wide range of widespread estimators. Besides, the question of model selection via cross-validation is considered through two approaches. The first one relies on the optimal estimation of the risk in terms of a bias-variance tradeoff, which results in a density estimation procedure based on a fully data-driven choice of p. This procedure is successfully applied to the multiple testing problem. The second approach is related to the interpretation of cross-validation in terms of penalized criterion. The quality of the leave-p-out procedure is theoretically assessed through oracle inequalities as well as an adaptivity result in the density estimation setup. The change-points detection problem is another concern of this work. It is explored through an extensive simulation study based on theoretical considerations. From this, we propose a fully resampling-based procedure, which enables to deal with the hard problem of heteroscedasticity, while keeping a reasonable computational complexity
François, Jérémie. "Fusion de connaissances expérimentales et expertes : une approche évolutive du diagnostic." Compiègne, 2000. http://www.theses.fr/2000COMP1308.
Повний текст джерелаNotin, Alban. "Evaluation à moindre coût de la fiabilité des structures sollicitées en fatigue." Compiègne, 2010. http://www.theses.fr/2010COMP1877.
Повний текст джерелаThis thesis take place in the context of the estimation of the reliability of structures under fatigue loading. In the case of industrial applications, each model evaluation may be time and storage consuming. This way, only a few number of evaluations can be performed. This efficient estimation of the reliability of structures under fatigue loading implies to word on the reliability algorithm as well as the speeding up of mechanical computations. In this double issue lies the settlement of this thesis. Concerning the reliability part, the RPCM (Resampling Polynomial Chaos Method) method has been developed. The goal is to build the polynomial chaos basis in an adaptative way such that the troncature error is taken into account. This erros is estimad through confidence intervals on the reliability index. Numerical results show a very good behaviour of the proposed method in the case of smooth limit-state functions. However, metamodels are not the only way to speed up computations. Another strategy consists in accelerate the mechanical computations by approximating the closest calculi controlling the error. This is the idea of the SLDL T (Stochastic LDL T decomposition) approach which is based on a slight modification of the Cholesky decomposition assuming that the fluctuations of the lower matrix L are negligible in the domain of variation of the random inputs. The randonmess is put on the digonal matrix D, which is optimized such a way to minimize the error on the stiffness matrix. In the case of a linear elastic mechanical behaviour with the Young’s modulus modeled by a random field, results show a gain factor round to 180
Bernard, Francis. "Méthodes d'analyse des données incomplètes incorporant l'incertitude attribuable aux valeurs manquantes." Mémoire, Université de Sherbrooke, 2013. http://hdl.handle.net/11143/6571.
Повний текст джерелаLusinchi, Dominic. "La statistique appliquée : usage et signification dans les sciences sociales : essai de recherche méthodologique basé sur des études de cas aux États-Unis." Paris 8, 2008. http://octaviana.fr/document/137824084#?c=0&m=0&s=0&cv=0.
Повний текст джерелаThis study examines the statistical tools available to social science practitioners. The last 30 years have witnessed a considerable development in statistical techniques, both numerical and graphical. This is in large part a result of the application of statistical methods to an ever increasing number of fields, and also of the emergence, barely 20 years ago, of the personal computer. Using real data from surveys and other studies conducted in the U. S. , this research will show how important problems that arise in empirical data can be tackled by relying on well-known as well as relatively recent statistical techniques. Applied statistics is not simply an array of procedures; it is above all a way of thinking about empirical data, specifically how to discriminate between real and chance effects. This research endeavors to show that the role of applied statistics is to reveal both the meaning of the data and their limitations. The application of statistical methods to empirical data can often act as a catalyst to stimulate the sociological imagination
Tremblay, Nicolas. "Réseaux et signal : des outils de traitement du signal pour l'analyse des réseaux." Thesis, Lyon, École normale supérieure, 2014. http://www.theses.fr/2014ENSL0938/document.
Повний текст джерелаThis thesis describes new tools specifically designed for the analysis of networks such as social, transportation, neuronal, protein, communication networks... These networks, along with the rapid expansion of electronic, IT and mobile technologies are increasingly monitored and measured. Adapted tools of analysis are therefore very much in demand, which need to be universal, powerful, and precise enough to be able to extract useful information from very different possibly large networks. To this end, a large community of researchers from various disciplines have concentrated their efforts on the analysis of graphs, well define mathematical tools modeling the interconnected structure of networks. Among all the considered directions of research, graph signal processing brings a new and promising vision : a signal is no longer defined on a regular n-dimensional topology, but on a particular topology defined by the graph. To apply these new ideas on the practical problems of network analysis paves the way to an analysis firmly rooted in signal processing theory. It is precisely this frontier between signal processing and network science that we explore throughout this thesis, as shown by two of its major contributions. Firstly, a multiscale version of community detection in networks is proposed, based on the recent definition of graph wavelets. Then, a network-adapted bootstrap method is introduced, that enables statistical estimation based on carefully designed graph resampling schemes
Delsol, Laurent. "Régression sur variable fonctionnelle : estimation, tests de structure et applications." Phd thesis, Université Paul Sabatier - Toulouse III, 2008. http://tel.archives-ouvertes.fr/tel-00449806.
Повний текст джерелаEl, Hage Mhamad. "Etude de la qualité géomorphologique de modèles numériques de terrain issus de l'imagerie spatiale." Phd thesis, Conservatoire national des arts et metiers - CNAM, 2012. http://tel.archives-ouvertes.fr/tel-00780682.
Повний текст джерелаMaillard, Guillaume. "Hold-out and Aggregated hold-out Aggregated Hold-Out Aggregated hold-out for sparse linear regression with a robust loss function." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASM005.
Повний текст джерелаIn statistics, it is often necessary to choose between different estimators (estimator selection) or to combine them (agregation). For risk-minimization problems, a simple method, called hold-out or validation, is to leave out some of the data, using it to estimate the risk of the estimators, in order to select the estimator with minimal risk. This method requires the statistician to arbitrarily select a subset of the data to form the "validation sample". The influence of this choice can be reduced by averaging several hold-out estimators (Aggregated hold-out, Agghoo). In this thesis, the hold-out and Agghoo are studied in various settings. First, theoretical guarantees for the hold-out (and Agghoo) are extended to two settings where the risk is unbounded: kernel methods and sparse linear regression. Secondly, a comprehensive analysis of the risk of both methods is carried out in a particular case: least-squares density estimation using Fourier series. It is proved that aggregated hold-out can perform better than the best estimator in the given collection, something that is clearly impossible for a procedure, such as hold-out or cross-validation, which selects only one estimator
Gaudnik, Cassandre. "Impacts des dépôts d'azote atmosphérique sur la végétation des prairies acides du domaine atlantique français : approche comparative et expérimentale." Thesis, Bordeaux 1, 2011. http://www.theses.fr/2011BOR14407/document.
Повний текст джерелаTo assess the impact of atmospheric nitrogen deposition on ecosystems, we werefocused on a patrimonial interest ecosystem: acid grasslands of Violion caninae. Within thesegrasslands, we aimed to (i) characterise temporal and spatial variation in plant speciescomposition along the French Atlantic domain and determine if nitrogen deposition andclimate variables could explain these patterns, (ii) understand processes underlined bynitrogen addition on vegetation and soil, and (iii) examine the potential conservation andrestoration ways.Temporal and spatial approach of acid grasslands brought to light changes in speciescomposition at local scale of community type but also at the national French Atlantic domainscale. At both local and national scale, these changes were linked to climate change withincrease of mean annual temperature and decrease of soil water availability. However at localscale, the most changes in species composition were experienced on sites with climate changeand also the highest chronic nitrogen deposition since the last 25 years. These changes inspecies composition occurred at the expense of short stature species like forbs whereasgrasses species were persistent and dominated vegetation. These changes are visible from 10-15 kg N ha-1 an-1, determined as the critical load for nitrogen in acid grasslands.The experiment allowed to highlight processes underlined in acid grasslands afternitrogen addition. In particular, nitrogen enrichment did not lead to light competition invegetation. These grasslands, mainly defined by poor-nutrient and low capacity to bufferacidity in soil, were essentially affected by ammonium toxicity or even acidification on thelong range.Finally, the study of conservation ways showed the difficulty to conserve and restorethe grasslands affected by nitrogen deposition. Indeed, more frequent cuttings with biomassremoval were useless in a system not influenced by light competition within vegetation. Thestudy of seed banks showed also that conservation ways could not be based just on seed banksto maintain characteristic species. These results highlight the importance to conserve theexisting acid grasslands, mostly in region with low ambient nitrogen deposition
Blanc, Philippe. "Développement de méthodes pour la détection de changement." Phd thesis, École Nationale Supérieure des Mines de Paris, 1999. http://tel.archives-ouvertes.fr/tel-00477115.
Повний текст джерелаCelisse, Alain. "Sélection de modèle par validation-croisée en estimation de la densité, régression et détection de ruptures." Phd thesis, Université Paris Sud - Paris XI, 2008. http://tel.archives-ouvertes.fr/tel-00346320.
Повний текст джерелаBruffaerts, Christopher. "Contributions to robust methods in nonparametric frontier models." Doctoral thesis, Universite Libre de Bruxelles, 2014. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209244.
Повний текст джерелаL’ensemble de production est l’ensemble contenant toutes les combinaisons d’inputs et d’outputs qui sont physiquement réalisables dans une économie. De cet ensemble contenant p inputs et q outputs, la notion d’efficacité d ‘une unité de production peut être définie. Celle-ci se définie comme une distance séparant le DMU de la frontière de l’ensemble de production. A partir d’un échantillon de DMUs, le but est de reconstruire cette frontière de production afin de pouvoir y évaluer l’efficacité des DMUs. A cette fin, le chercheur utilise très souvent des méthodes dites « classiques » telles que le « Data Envelopment Analysis » (DEA).
De nos jours, le statisticien bénéficie de plus en plus de données, ce qui veut également dire qu’il n’a pas l’opportunité de faire attention aux données qui font partie de sa base de données. Il se peut en effet que certaines valeurs aberrantes s’immiscent dans les jeux de données sans que nous y fassions particulièrement attention. En particulier, les modèles de frontières sont extrêmement sensibles aux valeurs aberrantes et peuvent fortement influencer l’inférence qui s’en suit. Pour éviter que certaines données n’entravent une analyse correcte, des méthodes robustes sont utilisées.
Allier le côté robuste au problème d’évaluation d’efficacité est l’objectif général de cette thèse. Le premier chapitre plante le décor en présentant la littérature existante dans ce domaine. Les quatre chapitres suivants sont organisés sous forme d’articles scientifiques.
Le chapitre 2 étudie les propriétés de robustesse d’un estimateur d’efficacité particulier. Cet estimateur mesure la distance entre le DMU analysé et la frontière de production le long d’un chemin hyperbolique passant par l’unité. Ce type de distance très spécifique s’avère très utile pour définir l’efficacité de type directionnel.
Le chapitre 3 est l’extension du premier article au cas de l’efficacité directionnelle. Ce type de distance généralise toutes les distances de type linéaires pour évaluer l’efficacité d’un DMU. En plus d’étudier les propriétés de robustesse de l’estimateur d’efficacité de type directionnel, une méthode de détection de valeurs aberrantes est présentée. Celle-ci s’avère très utile afin d’identifier les unités de production influençantes dans cet espace multidimensionnel (dimension p+q).
Le chapitre 4 présente les méthodes d’inférence pour les efficacités dans les modèles nonparamétriques de frontière. En particulier, les méthodes de rééchantillonnage comme le bootstrap ou le subsampling s’avère être très utiles. Dans un premier temps, cet article montre comment améliorer l’inférence sur les efficacités grâce au subsampling et prouve qu’il n’est pas suffisant d’utiliser un estimateur d’efficacité robuste dans les méthodes de rééchantillonnage pour avoir une inférence qui soit fiable. C’est pourquoi, dans un second temps, cet article propose une méthode robuste de rééchantillonnage qui est adaptée au problème d’évaluation d’efficacité.
Finalement, le dernier chapitre est une application empirique. Plus précisément, cette analyse s’intéresse à l ‘efficacité des universités américaines publiques et privées au niveau de leur recherche. Des méthodes classiques et robustes sont utilisées afin de montrer comment tous les outils étudiés précédemment peuvent s’appliquer en pratique. En particulier, cette étude permet d’étudier l’impact sur l’efficacité des institutions américaines de certaines variables telles que l’enseignement, l’internationalisation ou la collaboration avec le monde de l’industrie.
Doctorat en sciences, Orientation statistique
info:eu-repo/semantics/nonPublished
Rohmer, Tom. "Deux tests de détection de rupture dans la copule d'observations multivariées." Thèse, Université de Sherbrooke, 2014. http://hdl.handle.net/11143/5933.
Повний текст джерелаHage, Mhamad El. "Etude de la qualité géomorphologique de modèles numériques de terrain issus de l’imagerie spatiale." Thesis, Paris, CNAM, 2012. http://www.theses.fr/2012CNAM0846/document.
Повний текст джерелаThe production of Digital Elevation Models (DEMs) has undergone significant evolution duringthe last two decades resulting from a growing demand for scientific as well as industrial purposes.Many Earth observation satellites, using optical and radar sensors, have enabled the production ofDEMs covering most of the Earth’s surface. The algorithms of image and point cloud processing havealso undergone significant evolution. This progress has provided DEMs on different scales, which canfulfill the requirements of many users. The applications based on geomorphology have benefitted fromthis evolution. Indeed, these applications concentrate specifically on landforms for which the DEMconstitutes a basic data.The aim of this study is to assess the impact of the parameters of DEM production byphotogrammetry and InSAR on position and shape quality. The position quality, assessed by DEMproducers, is not sufficient for the evaluation of shape quality. Thus, the evaluation methods ofposition and shape quality and the difference between them are described. A novel method of internalvalidation, which does not require reference data, is proposed. Then, the impact of image matchingand interferometric processing parameters as well as resampling, on elevation and shapes, is assessed.Finally, we conclude on recommendations on how to choose the production parameters correctly,particularly for photogrammetry.We observe little impact from most of the parameters on the elevation, except InSAR parameters.On the other hand, there is a significant impact on the elevation derivatives. The impact of matchingparameters presents a strong dependence on the terrain morphology and the landcover. Therefore,these parameters have to be selected by taking into account these two factors. The effect ofinterferometric processing manifests by phase unwrapping errors that mainly affect the elevation andless the derivatives. The interpolation methods and the mesh size present a small impact on theelevation and a significant impact on the derivatives. Indeed, the value of the derivatives and theirquality depend directly on the mesh size. The selection of this size has to be made according to theforeseen application. Finally, we conclude that these parameters are interdependent and can havesimilar effects. They must be selected according to the foreseen application, the terrain morphologyand the landcover in order to minimize the error in the final results and the conclusions
Lamberti, Roland. "Contributions aux méthodes de Monte Carlo et leur application au filtrage statistique." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLL007/document.
Повний текст джерелаThis thesis deals with integration calculus in the context of Bayesian inference and Bayesian statistical filtering. More precisely, we focus on Monte Carlo integration methods. We first revisit the importance sampling with resampling mechanism, then its extension to the dynamic setting known as particle filtering, and finally conclude our work with a multi-target tracking application. Firstly, we consider the problem of estimating some moment of a probability density, known up to a constant, via Monte Carlo methodology. We start by proposing a new estimator affiliated with the normalized importance sampling estimator but using two proposition densities rather than a single one. We then revisit the importance sampling with resampling mechanism as a whole in order to produce Monte Carlo samples that are independent, contrary to the classical mechanism, which enables us to develop two new estimators. Secondly, we consider the dynamic aspect in the framework of sequential Bayesian inference. We thus adapt to this framework our new independent resampling technique, previously developed in a static setting. This yields the particle filtering with independent resampling mechanism, which we reinterpret as a special case of auxiliary particle filtering. Because of the increased cost required by this technique, we next propose a semi independent resampling procedure which enables to control this additional cost. Lastly, we consider an application of multi-target tracking within a sensor network using a new Bayesian model, and empirically analyze the results from our new particle filtering algorithm as well as a sequential Markov Chain Monte Carlo algorithm
Donat-Bouillud, Pierre. "Models, Analysis and Execution of Audio Graphs in Interactive Multimedia Systems." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS604.
Повний текст джерелаInteractive Multimedia Systems (IMSs) are used in concert for interactive performances, which combine in real time acoustic instruments, electronic instruments, data from various sensors (gestures, midi interface, etc.) and the control of different media (video, light, etc.). This thesis presents a formal model of audio graphs, via a type system and a denotational semantics, with multirate timestamped bufferized data streams that make it possible to represent with more or less precision the interleaving of the control (for example a low frequency oscillator, velocities from an accelerometer) and audio processing in an MIS. An audio extension of Antescofo, an IMS that acts as a score follower and includes a dedicated synchronous timed language, has motivated the development of this model. This extension makes it possible to connect Faust effects and native effects on the fly safely. The approach has been validated on a mixed music piece and an example of audio and video interactions. At last, this thesis proposes offline optimizations based on the automatic resampling of parts of an audio graph to be executed. A quality and execution time model in the graph has been defined. Its experimental study was carried out using a prototype IMS based on the automatic generation of audio graphs, which has also made it possible to characterize resampling strategies proposed for the online case in real time
Li, Weiyu. "Quelques contributions à l'estimation des modèles définis par des équations estimantes conditionnelles." Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S065/document.
Повний текст джерелаIn this dissertation we study statistical models defined by condition estimating equations. Many statistical models could be stated under this form (mean regression, quantile regression, transformation models, instrumental variable models, etc.). We consider models with finite dimensional unknown parameter, as well as semiparametric models involving an additional infinite dimensional parameter. In the latter case, we focus on single-index models that realize an appealing compromise between parametric specifications, simple and leading to accurate estimates, but too restrictive and likely misspecified, and the nonparametric approaches, flexible but suffering from the curse of dimensionality. In particular, we study the single-index models in the presence of random censoring. The guiding line of our study is a U-statistics which allows to estimate the unknown parameters in a wide spectrum of models
Calle, Didier. "Agrandissement d'images par synthèse de similarités et par induction sur un ensemble." Phd thesis, Université Joseph Fourier (Grenoble), 1999. http://tel.archives-ouvertes.fr/tel-00004813.
Повний текст джерелаBécu, Jean-Michel. "Contrôle des fausses découvertes lors de la sélection de variables en grande dimension." Thesis, Compiègne, 2016. http://www.theses.fr/2016COMP2264/document.
Повний текст джерелаIn the regression framework, many studies are focused on the high-dimensional problem where the number of measured explanatory variables is very large compared to the sample size. If variable selection is a classical question, usual methods are not applicable in the high-dimensional case. So, in this manuscript, we develop the transposition of statistical tests to the high dimension. These tests operate on estimates of regression coefficients obtained by penalized linear regression, which is applicable in high-dimension. The main objective of these tests is the false discovery control. The first contribution of this manuscript provides a quantification of the uncertainty for regression coefficients estimated by ridge regression in high dimension. The Ridge regression penalizes the coefficients on their l2 norm. To do this, we devise a statistical test based on permutations. The second contribution is based on a two-step selection approach. A first step is dedicated to the screening of variables, based on parsimonious regression Lasso. The second step consists in cleaning the resulting set by testing the relevance of pre-selected variables. These tests are made on adaptive-ridge estimates, where the penalty is constructed on Lasso estimates learned during the screening step. A last contribution consists to the transposition of this approach to group-variables selection
Magalhães, Nelo. "Validation croisée et pénalisation pour l'estimation de densité." Thesis, Paris 11, 2015. http://www.theses.fr/2015PA112100/document.
Повний текст джерелаThis thesis takes place in the density estimation setting from a nonparametric and nonasymptotic point of view. It concerns the statistical algorithm selection problem which generalizes, among others, the problem of model and bandwidth selection. We study classical procedures, such as penalization or resampling procedures (in particular V-fold cross-validation), which evaluate an algorithm by estimating its risk. We provide, thanks to concentration inequalities, an optimal penalty for selecting a linear estimator and we prove oracle inequalities and adaptative properties for resampling procedures. Moreover, new resampling procedure, based on estimator comparison by the mean of robust tests, is introduced as an alternative to procedures relying on the unbiased risk estimation principle. A second goal of this work is to compare these procedures from a theoretical point of view and to understand the role of V for V-fold penalization. We validate these theoretical results on empirical studies
Mashreghi, Zeinab. "Méthodes de rééchantillonnage en méthodologie d'enquête." Thèse, 2014. http://hdl.handle.net/1866/11933.
Повний текст джерелаThe aim of this thesis is to study the bootstrap variance estimators of a statistic based on imputed survey data. Applying a bootstrap method designed for complete survey data (full response) in the presence of imputed values and treating them as true observations may lead to underestimation of the variance. In this context, Shao and Sitter (1996) introduced a bootstrap procedure in which the variable under study and the response status are bootstrapped together and bootstrap non-respondents are imputed using the imputation method applied on the original sample. The resulting bootstrap variance estimator is valid when the sampling fraction is small. In Chapter 1, we begin by doing a survey of the existing bootstrap methods for (complete and imputed) survey data and, for the first time in the literature, present them in a unified framework. In Chapter 2, we introduce a new bootstrap procedure to estimate the variance under the non-response model approach when the uniform non-response mechanism is assumed. Using only information about the response rate, unlike Shao and Sitter (1996) which requires the individual response status, the bootstrap response status is generated for each selected bootstrap sample leading to a valid bootstrap variance estimator even for non-negligible sampling fractions. In Chapter 3, we investigate pseudo-population bootstrap approaches and we consider a more general class of non-response mechanisms. We develop two pseudo-population bootstrap procedures to estimate the variance of an imputed estimator with respect to the non-response model and the imputation model approaches. These procedures are also valid even for non-negligible sampling fractions.
Charlebois, Joanne. "Choix des poids de l'estimateur de vraisemblance pondérée par rééchantillonnage." Thèse, 2007. http://hdl.handle.net/1866/18131.
Повний текст джерелаOuhib, Lyes. "Modélisation des apports naturels de réservoirs." Thèse, 2005. http://hdl.handle.net/1866/17787.
Повний текст джерела