Dissertationen zum Thema „Statistique de test“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Dissertationen für die Forschung zum Thema "Statistique de test" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Dissertationen für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
Gouraud, Sandrine-Dominique. „Utilisation des Structures Combinatoires pour le Test Statistique“. Phd thesis, Université Paris Sud - Paris XI, 2004. http://tel.archives-ouvertes.fr/tel-00011191.
Der volle Inhalt der Quellelogiciel à partir d'une description graphique des comportements du
système à tester (graphe de contrôle, statecharts). Son originalité
repose sur la combinaison de résultats et d'outils de combinatoire
(génération aléatoire de structures combinatoires) et d'un solveur de
contraintes, pour obtenir une méthode de test complètement automatisée.
Contrairement aux approches classiques qui tirent des entrées, la
génération aléatoire uniforme est utilisée pour tirer des chemins parmi
un ensemble de chemins d'exécution ou de traces du système à tester.
Puis, une étape de résolution de contraintes est utilisée pour
déterminer les entrées qui permettront d'exécuter ces chemins.
De plus, nous montrons comment les techniques de programmation
linéaire peuvent améliorer la qualité d'un ensemble de tests.
Une première application a été effectuée pour le test statistique
structurel défini par Thévenod-Fosse et Waeselynck (LAAS) et un
prototype a été développé.
Des expériences (plus de 10000 réalisées sur quatre fonctions issues
d'un logiciel industriel) ont été effectuées pour évaluer notre approche
et sa stabilité.
Ces expériences montrent que notre approche est comparable à celle
du LAAS, est stable et a l'avantage d'être complètement automatisée.
Ces premières expériences nous permettent également d'envisager un
passage à l'échelle de notre approche. Plus généralement, ces travaux
pourraient servir de base pour une nouvelle classe d'outils dans le
domaine du test de logiciel, combinant génération aléatoire de
structures combinatoires, techniques de programmation linéaire et
résolution de contraintes.
Bonnardel, Philippe. „Test statistique Kappa : programmation informatique et applications pratiques“. Paris 5, 1996. http://www.theses.fr/1996PA05P072.
Der volle Inhalt der QuelleWaeselynck, Hélène. „Vérification de logiciels critiques par le test statistique“. Toulouse, INPT, 1993. http://www.theses.fr/1993INPT010H.
Der volle Inhalt der QuelleSaumard, Mathieu. „Contribution à l'analyse statistique des données fontionnelles“. Thesis, Rennes, INSA, 2013. http://www.theses.fr/2013ISAR0009/document.
Der volle Inhalt der QuelleIn this thesis, we are interested in the functional data. The problem of estimation in a model of estimating equations is studying. We derive a central limit type theorem for the considered estimator. The optimal instruments are estimated, and we obtain a uniform convergence of the estimators. We are then interested in various testing with functional data. We study the problem of nonparametric testing for the effect of a random functional covariate on an error term which could be directly observed as a response or estimated from a functional model like for instance the functional linear model. We proved, in order to construct the tests, a result of dimension reduction which relies on projections of the functional covariate. We have constructed no-effect tests by using a kernel smoothing or a nearest neighbor smoothing. A goodness-of-fit test in the functional linear model is also proposed. All these tests are studied from a theoretical and practical perspective
Oudinet, Johan. „Approches combinatoires pour le test statistique à grande échelle“. Paris 11, 2010. http://www.theses.fr/2010PA112347.
Der volle Inhalt der QuelleThis thesis focuses on the development of combinatorial methods for testing and formal verification. Particularly on probabilistic approaches because exhaustive verification is often not tractable for complex systems. For model-based testing, I guide the random exploration of the model to ensure a satisfaction with desired probability of the expected coverage criterion, regardless of the underlying topology of the explored model. Regarding model-checking, I show how to generate a random number of finite paths to check if a property is satisfied with a certain probability. In the first part, I compare different algorithms for generating uniformly at random paths in an automaton. Then I propose a new algorithm that offers a good compromise with a sub-linear space complexity in the path length and a almost-linear time complexity. This algorithm allows the exploration of large models (tens of millions of states) by generating long paths (hundreds of thousands of transitions). In a second part, I present a way to combine partial order reduction and on-the-fly generation techniques to explore concurrent systems without constructing the global model, but relying on models of the components only. Finally, I show how to bias the previous algorithms to satisfy other coverage criteria. When a criterion is not based on paths, but on a set of states or transitions, we use a mixed solution to ensure both various ways of exploring those states or transitions and the criterion satisfaction with a desired probability
Petit, Matthieu. „Test statistique structurel par résolution par contraintes de choix probabiliste“. Rennes 1, 2008. ftp://ftp.irisa.fr/techreports/theses/2008/petit.pdf.
Der volle Inhalt der QuelleIn this thesis, a method to automatically generate test data at random is proposed. The test data generator respects strong probabilistic properties: uniform selection of feasible paths that satisfy the coverage of structural testing criteria and uniform selection of test data that execute the selected paths. We combine stochastic and constraint modelling to address the statistical test data generation problem. Stochastic modelling is based on the assumption that the distribution probability is known. We define probabilistic choice constraints to reason on random variables whose probability distribution is only partially known. In this framework, uniform selection of feasible paths is expressed as a problem of probabilistic choice constraints. An algorithm is proposed to generate uniformly test data that activate a path. GENETTA tools permits to validate the statistical test data generator. This tool uses our library of probabilistic choice constraints PCC(FD)
Petit, Matthieu Jensen Thomas. „Test statistique structurel par résolution par contraintes de choix probabiliste“. Rennes : [s.n.], 2008. ftp://ftp.irisa.fr/techreports/theses/2008/petit.pdf.
Der volle Inhalt der QuelleLacombe, Jean-Pierre. „Analyse statistique de processus de poisson non homogènes. Traitement statistique d'un multidétecteur de particules“. Phd thesis, Grenoble 1, 1985. http://tel.archives-ouvertes.fr/tel-00318875.
Der volle Inhalt der QuelleDUCHENE, CHRISTINE. „Test statistique de la validite des modeles oceaniques equatoriaux a l'aide d'observations“. Paris 6, 1989. http://www.theses.fr/1989PA066164.
Der volle Inhalt der QuelleFalissard, Bruno. „Les analyses intermediaires dans les essais therapeutiques“. Paris 11, 1990. http://www.theses.fr/1990PA11T008.
Der volle Inhalt der QuelleNze, Ossima Arnaud Davin. „Evaluation statistique des outils diagnostiques et pronostiques à l'aide des surfaces ROC“. Thesis, Montpellier 1, 2014. http://www.theses.fr/2014MON1T005/document.
Der volle Inhalt der QuelleIn diagnostic medical, the receiver operating characteristic (ROC) surface is the statistical tool used to assess the accuracy of a diagnostic test in discriminating three disease states, and the volume under the ROC surface is the used index for the quantification of the performance of the test. In some situations, various factors can affect the test results and subsequently the accuracy measures. In the case of longitudinal studies, the patient's status may change over time. In this manuscript, we developed statistical methods to assess the discriminatory capabilities of diagnostic and pronostic tools. We first proposed a semiparametric method for estimating ROC surface under density ratio models. The construction of the proposed method is based on the adjacent-category logit model and the empirical likelihood approach. We described the bootstrap method for inference of the obtained estimators. Next, we presented a method for estimating ROC surfaces called Lehmann family ROC surfaces. This method is based on the family of Lehmann alternatives or proportional hazards model. It has the advantage of taking into account covariates that may affect the accuracy of a diagnostic test. Moreover, we have developed a covariate-specific ROC surface based on the Bayes rule. For that, we proposed semiparametric estimator for covariate-specific ROC surfaces via polytomous logistic regression procedures and a semiparametric location model. Finally, in the case where patient's status may evolve through different stages of disease a method of time-dependent ROC surfaces was developed. The proposed estimator uses the "Inverse Probability of Censoring Weighting" (IPCW) approach. Simulations and examples are provided to illustrate the performance of the proposed estimators
Leconte-Lavaud, Evelyne. „Modeles et tests pour l'analyse statistique des donnees censurees multivariees“. Paris 11, 1995. http://www.theses.fr/1995PA11T014.
Der volle Inhalt der QuelleLe, Guen Hélène. „Validation d'un logiciel par le test statistique d'usage : de la modélisation à la décision de livraison“. Rennes 1, 2005. http://www.theses.fr/2005REN1S049.
Der volle Inhalt der QuelleDupuis, Jérôme. „Analyse statistique bayesienne de modèles de capture-recapture“. Paris 6, 1995. http://www.theses.fr/1995PA066077.
Der volle Inhalt der QuelleIgnaccolo, Rosaria. „Tests d'ajustement fonctionnels pour des observations corrélées“. Paris 6, 2002. http://www.theses.fr/2002PA066416.
Der volle Inhalt der QuelleRibes, Aurélien. „Détection statistique des changements climatiques“. Phd thesis, Université Paul Sabatier - Toulouse III, 2009. http://tel.archives-ouvertes.fr/tel-00439861.
Der volle Inhalt der QuelleAkkouche, Nourredine. „Optimisation du test de production de circuits analogiques et RF par des techniques de modélisation statistique“. Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00625469.
Der volle Inhalt der QuelleCénac, Peggy. „Étude statistique de séquences biologiques et convergence de martingales“. Toulouse 3, 2006. http://www.theses.fr/2006TOU30065.
Der volle Inhalt der QuelleThe Chaos Game Representation is a dynamical system which maps a sequence of letters taken from a finite alphabet onto an empirical measure on a set. We show how the CGR can be used to characterize the order of an homogeneous Markov chain and to define a new family of tests. Then we propose a construction of Digital Search Trees, inspired from the CGR, by successively inserting all the returned prefixes of a Markov chain. We give the asymptotic behavior of the critical lengths of paths, which turns out to be, at first order, the same one as in the case of DST built from independent Markov chains. A last part deals with properties of almost sure convergence of vectorial martingales. Under suitable regularity conditions on the growing process, we establish the convergence of normalized moments of all orders in the almost sure central limit theorem. The results are applied to the cumulated errors of estimation and prediction in linear regression models and branching processes
Ben, Ghorbal Noomen. „Étude de certaines mesures d'association multivariées et d'un test de dépendance extrémale fondés sur les rangs“. Thesis, Université Laval, 2010. http://www.theses.ulaval.ca/2010/27602/27602.pdf.
Der volle Inhalt der QuelleBousquet, Lydie du. „Test fonctionnel statistique de logiciels spécifiés en Lustre : application à la validation de services téléphoniques“. Université Joseph Fourier (Grenoble), 1999. http://tel.archives-ouvertes.fr/tel-00004828.
Der volle Inhalt der QuellePeyre, Julie. „Analyse statistique des données issues des biopuces à ADN“. Phd thesis, Université Joseph Fourier (Grenoble), 2005. http://tel.archives-ouvertes.fr/tel-00012041.
Der volle Inhalt der QuelleDans un premier chapitre, nous étudions le problème de la normalisation des données dont l'objectif est d'éliminer les variations parasites entre les échantillons des populations pour ne conserver que les variations expliquées par les phénomènes biologiques. Nous présentons plusieurs méthodes existantes pour lesquelles nous proposons des améliorations. Pour guider le choix d'une méthode de normalisation, une méthode de simulation de données de biopuces est mise au point.
Dans un deuxième chapitre, nous abordons le problème de la détection de gènes différentiellement exprimés entre deux séries d'expériences. On se ramène ici à un problème de test d'hypothèses multiples. Plusieurs approches sont envisagées : sélection de modèles et pénalisation, méthode FDR basée sur une décomposition en ondelettes des statistiques de test ou encore seuillage bayésien.
Dans le dernier chapitre, nous considérons les problèmes de classification supervisée pour les données de biopuces. Pour remédier au problème du "fléau de la dimension", nous avons développé une méthode semi-paramétrique de réduction de dimension, basée sur la maximisation d'un critère de vraisemblance locale dans les modèles linéaires généralisés en indice simple. L'étape de réduction de dimension est alors suivie d'une étape de régression par polynômes locaux pour effectuer la classification supervisée des individus considérés.
Vimond, Myriam. „Inférence statistique par des transformées de Fourier pour des modèles de régression semi-paramétriques“. Phd thesis, Université Paul Sabatier - Toulouse III, 2007. http://tel.archives-ouvertes.fr/tel-00185102.
Der volle Inhalt der QuelleDjeddour, Khédidja. „Estimation récursive du mode et de la valeur modale d'une densité : test d'ajustement de loi“. Versailles-St Quentin en Yvelines, 2003. http://www.theses.fr/2003VERS0016.
Der volle Inhalt der QuelleFontez, Bénédicte. „Test d'adéquation des résidus pour la régression non-linéaire. Application aux courbes de croissance en foresterie“. Montpellier 2, 2001. http://www.theses.fr/2001MON20005.
Der volle Inhalt der QuelleChevalley, Philippe. „Approche statistique pour le test de logiciels critiques orientés-objet : expérimentation sur un logiciel avionique“. École nationale supérieure de l'aéronautique et de l'espace (Toulouse ; 1972-2007), 2001. http://www.theses.fr/2001ESAE0018.
Der volle Inhalt der QuelleRossi, Sandrine. „Test d'hypothèses dans la découverte de règles : nouvelles approches du pistage des stratégies de confirmation et d'infirmation d'hypothèses“. Aix-Marseille 1, 1999. http://www.theses.fr/1999AIX10001.
Der volle Inhalt der QuelleSerra, Roger. „Sur une approche statistique de l'identification modale des structures“. Besançon, 1999. http://www.theses.fr/1999BESA2055.
Der volle Inhalt der QuelleGhorbanzadeh, Dariush. „Détection de rupture dans les modèles statistiques“. Paris 7, 1992. http://www.theses.fr/1992PA077246.
Der volle Inhalt der QuelleAkkouche, N. „Optimisation du test de production de circuits analogiques et RF par des techniques de modélisation statistique“. Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00669605.
Der volle Inhalt der QuelleRasoafaraniaina, Rondrotiana J. „Preliminary test estimation in uniformly locally and asymptotically normal models“. Doctoral thesis, Universite Libre de Bruxelles, 2020. https://dipot.ulb.ac.be/dspace/bitstream/2013/312253/4/Contents.pdf.
Der volle Inhalt der QuelleDoctorat en Sciences
info:eu-repo/semantics/nonPublished
Cenac, Peggy. „Etude statistique de séquences biologiques et convergence de martingales“. Phd thesis, Université Paul Sabatier - Toulouse III, 2006. http://tel.archives-ouvertes.fr/tel-00134328.
Der volle Inhalt der Quelleque les méthodes de comptage de mots classiques ? A
partir d'une caractérisation basée sur la CGR, on propose une nouvelle famille de
tests donnant l'ordre d'une chaîne de Markov homogène.
On définit ensuite une construction d'arbres digitaux de recherche,
inspirés par la CGR, en insérant successivement les préfixes retournés d'une chaîne de Markov. On montre que les longueurs des branches critiques se comportent, au premier ordre, comme si les
séquences insérées étaient indépendantes entre elles.
La dernière partie est consacrée à l'étude de la convergence presque sûre des moments normalisés de tout ordre de martingales vectorielles dans le théorème de la limite centrale
presque sûr. Les résultats sont appliqués aux erreurs d'estimation et de prédiction dans les régressions linéaires et les processus de branchement.
FERRIGNO, Sandie. „Un test d'adéquation global pour la fonction de répartition conditionnelle“. Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2004. http://tel.archives-ouvertes.fr/tel-00008559.
Der volle Inhalt der Quellel'on doit valider pour justifier son utilisation. Dans ce travail, on propose une approche globale où toutes les hypothèses faites pour asseoir ce modèle sont testées simultanément.
Plus précisément, on construit un test basé sur une quantité qui permet de canaliser toute l'information liant X à Y : la fonction de répartition conditionnelle de Y sachant (X = x) définie par F(y|x)=P(Y<=y|X=x). Notre test compare la valeur prise par l'estimateur polynômial local de F(y|x) à une estimation paramétrique du modèle supposé et rejette sa
validité si la distance entre ces deux quantités est trop grande. Dans un premier temps, on considère le cas où la fonction de répartition supposée est entièrement spécifiée et, dans
ce contexte, on établit le comportement asymptotique du test. Dans la deuxième partie du travail, on généralise ce résultat au cas plus courant en pratique où le modèle supposé contient un certain nombre de paramètres inconnus. On étudie ensuite la puissance locale du test en déterminant son comportement asymptotique local sous des suites d'hypothèses contigües. Enfin, on propose un critère de choix de la fenêtre d'ajustement qui intervient lors de l'étape d'estimation polynômiale locale de la fonction de répartition conditionnelle.
Alves, Fonseca Renan. „Test et Fiabilité des Mémoires SRAM“. Thesis, Montpellier 2, 2011. http://www.theses.fr/2011MON20055/document.
Der volle Inhalt der QuelleNowadays, Static Random Access Memories (SRAM) are made with the fastest technologies and are among the most important components in complex systems. SRAM bit-cell transistors are often designed using the minimal dimensions of the technology node. As a consequence, SRAMs are more sensitive to new physical phenomena that occur in these technologies, and hence are extremely vulnerable to physical defects. In order to detect whether each component is defective or not, high cost test procedures are employed. Different issues related to this test procedure were studied during this thesis, and are compiled in this document. One of the main contributions of this thesis was to establish a method to set the environmental conditions during the test procedure in order to capture non-deterministic faults. Since statistical simulations are often used to deal with non-deterministic faults, an efficient statistical simulation method was specially conceived for the 6 transistors SRAM bit-cell. In this thesis, we equally deal with fault characterization, variability characterization and fault tolerance
d'Estampes, Ludovic. „Traitement statistique des processus alpha-stables: mesures de dépendance et identification des ar stables. Test séquentiels tronqués“. Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2003. http://tel.archives-ouvertes.fr/tel-00005216.
Der volle Inhalt der QuelleCharles, Olivier. „Application des hypothèses de test à une définition de la couverture“. Nancy 1, 1997. http://www.theses.fr/1997NAN10255.
Der volle Inhalt der QuelleConformance testing aims at checking that a product complies to the requirements for which it has been developed. Because of their complexity, communicating systems cannot be tested exhaustively. In practice, real tests are incomplete and never perfect. The goal of test coverage is to express this imperfection. So, it is an important measure for test selection and automatic test generation. When selecting test suites, test experts make choices based on test hypotheses. In other words, their experience of testing allows them to infer some good properties on the imlementation which decrease test effort. In this thesis, we propose to define H-coverage as the set of hypotheses which must be made such that the implementation is equivalent to the exhaustive test. In a first part, we precisely define H-coverage and we show that it is necessary to have a formalism available to write hypotheses in order to compute this measure. In a second part we solve the problem for a particular set of systems : the input outputautomata. First we propose to write hypotheses through trace sets, and then as automata transformers
Chokri, Khalid. „Contributions à l'inférence statistique dans les modèles de régression partiellement linéaires additifs“. Thesis, Paris 6, 2014. http://www.theses.fr/2014PA066439/document.
Der volle Inhalt der QuelleParametric regression models provide powerful tools for analyzing practical data when the models are correctly specified, but may suffer from large modelling biases when structures of the models are misspecified. As an alternative, nonparametric smoothing methods eases the concerns on modelling biases. However, nonparametric models are hampered by the so-called curse of dimensionality in multivariate settings. One of the methods for attenuating this difficulty is to model covariate effects via a partially linear structure, a combination of linear and nonlinear parts. To reduce the dimension impact in the estimation of the nonlinear part of the partially linear regression model, we introduce an additive structure of this part which induces, finally, a partially linear additive model. Our aim in this work is to establish some limit results pertaining to various parameters of the model (consistency, rate of convergence, asymptotic normality and iterated logarithm law) and to construct some hypotheses testing procedures related to the model structure, as the additivity of the nonlinear part, and to its parameters
Vu, Thi Lan Huong. „Analyse statistique locale de textures browniennes multifractionnaires anisotropes“. Thesis, Aix-Marseille, 2019. http://www.theses.fr/2019AIXM0094.
Der volle Inhalt der QuelleWe deal with some anisotropic extensions of the multifractional brownian fields that account for spatial phenomena whose properties of regularity and directionality may both vary in space. Our aim is to set statistical tests to decide whether an observed field of this kind is heterogeneous or not. The statistical methodology relies upon a field analysis by quadratic variations, which are averages of square field increments. Specific to our approach, these variations are computed locally in several directions. We establish an asymptotic result showing a linear gaussian relationship between these variations and parameters related to regularity and directional properties of the model. Using this result, we then design a test procedure based on Fisher statistics of linear gaussian models. Eventually we evaluate this procedure on simulated data. Finally, we design some algorithms for the segmentation of an image into regions of homogeneous textures. The first algorithm is based on a K-means procedure which has estimated parameters as input and takes into account their theoretical probability distributions. The second algorithm is based on an EM algorithm which involves continuous execution ateach 2-process loop (E) and (M). The values found in (E) and (M) at each loop will be used for calculations in the next loop. Eventually, we present an application of these algorithms in the context of a pluridisciplinary project which aims at optimizing the deployment of photo-voltaic panels on the ground. We deal with a preprocessing step of the project which concerns the segmentation of images from the satellite Sentinel-2 into regions where the cloud cover is homogeneous
Massiot, Gaspar. „Quelques Problèmes de Statistique autour des processus de Poisson“. Thesis, Rennes, École normale supérieure, 2017. http://www.theses.fr/2017ENSR0006/document.
Der volle Inhalt der QuelleThe main purpose of this thesis is to develop statistical methodologies for stochastic processes data and more precisely Cox process data.The problems considered arise from three different contexts: nonparametric tests, nonparametric kernel estimation and minimax estimation.We first study the statistical test problem of detecting wether a Cox process is Poisson or not.Then, we introduce a semiparametric estimate of the regression over a Poisson point process. Using Itô’s famous chaos expansion for Poisson functionals, we derive asymptotic minimax properties of our estimator.Finally, we introduce a nonparametric estimate of the intensity of a Cox process whenever it is a deterministic function of a known coprocess
Otari, Suzan. „Optimisation des procédures de tests pour simulation de transport des systèmes d'emballage, à partir de l'analyse statistique et fréquentielle du signal vibratoire excitateur“. Thesis, Reims, 2011. http://www.theses.fr/2011REIMS034.
Der volle Inhalt der QuelleSeveral tests are used to qualify a packaging or a packaging system aimed for transportation. This is called qualification plan. Random vibration tests are an efficient way to simulate the mechanical vibratory effects caused by transportation. The usual method is only concerned with the frequency distribution pattern of the signal using the average power spectral density (PSD) but statistical distribution of levels is totally ignored.In this work we have proposed a statistical model based on analyse of instantaneous acceleration levels of road transport, which identify and characterise the vibration signal. Continuous recording of acceleration signal all along the journey permits confirmation that this statistical distribution is not a Gaussian distribution but a modified Gaussian distribution, for which parameters are estimated and discussed. Therefore, it is possible to evaluate the transport severity by working out the appearance probability of acceleration levels greater than a fixed threshold and also the difference between the experimental distribution and the Gaussian distribution with the same rms value. This model is used to correcting the way of simulation in a test laboratory (chapter 5).Usually to recreate the mechanical effects of a vibration signal in the test laboratory, we use a partial recording of this signal without any adequate attention on effects of the recording parameters on characteristics of signal recorded in this way. In this work (chapter 3 and 4), the effects of partial recording is studied on statistical and frequency characteristics of acceleration signal. We have shown that for a road transport in France only 10% of the total duration of a journey must be taken to represent the whole journey. If the recording is performed with rates below 10%, we are able to estimate the error introduced on the distribution of signal and also on the level of the PSD. So this error can be corrected when the journey is simulated in laboratory.Finally we have proposed an alternative method for simulating the non-stationary and non-Gaussian signal with a typically used vibration system for this purpose which consists of a sequence of Gaussian signals. This method was proposed considering the means and materials available at company (Metropack) and enables them to simulate vibration effects in the most realistic way
Tessier, Maxime. „Étude de la performance d’un test d’association génétique pour des données familiales de survie en présence d’un biais de sélection“. Master's thesis, Université Laval, 2020. http://hdl.handle.net/20.500.11794/66872.
Der volle Inhalt der QuelleIn Leclerc et al. (2015, Genetic Epidemiology, 39 (6), 406-414), an association test between a group of genetic variants and censored phenotypes in presence of intrafamilial correlation is proposed. This test was implemented in a R package named gyriq. In this master’s thesis,we evaluate, with simulations, the performance of this test in presence of a sampling bias which stems from the data collection protocol. Indeed, in many situations, medical data from a family are considered if and only if a particular member of this family, called proband, is diagnosed with the event of interest during his medical exam. We develop multiple strategies to generate biased data according to such data collection protocol. We examine type 1 error and power of the association test in presence of such data, in the cases where there are 1 or more probands and when we sample only families where the probands have the event of interest or when we also sample a small proportion of families where the event has not occured for the probands. We conclude that the association test remains valid in presence of a selection bias but that the test power is diminished. Furthermore, the test is not valid when we include families where the event of interest has not occured for the probands.
El, bouch Sara. „Un test de normalité pour les séries temporelles multivariées, une application en sismologie“. Electronic Thesis or Diss., Université Grenoble Alpes, 2022. http://www.theses.fr/2022GRALT112.
Der volle Inhalt der QuelleThis thesis is concerned with time-series analysis. The present growth of interest in sensor networks and our ability to simultaneously record time series representing the fluctuations of numerous physical quantities, naturally leads to consider d-dimensional processes. Adapted tools for the extraction of knowledge from the ever increasing amount of recorded time-series are very much solicited. An equally exploding number of new models is developed as a response to the demand and considerable effort is put to developing efficient methods from theoretical and practical viewpoints.Change detection is a longstanding and interdisciplinary problem at the frontier of statistics and Machine Learning practices. In particular, we are interested in the detection of rare, brief and oscillating events that appear as non-Gaussian in data recorded simultaneously on sensors. This work describes a sequential detector for non-Gaussian colored time-series embedded in Gaussian noise.To this end, we explore tools at the frontier of estimation and detection and Machine Learning practices relevant to time-series analysis.Our major contributions consist of deriving the challenging (but relevant) limiting distribution of Mardia's Kurtosis for bivariate time-series, then extending the findings to the general multivariate case by means of random projections. The proposed results are translated to an operational sequential detector. Its performances are tested on colored copula, synthetic and real data. The good detection power of the bivariate detector is confirmed by computer experiments.Our work is also adjacent to applications in seismology, therefore our detector is merged with this framework and applied to seismograms recorded on three-axis sensors, and arrays of sensors
Nedelec, Thomas. „Apprentissage statistique contre des agents stratégiques et non-stratégiques, avec application à la théorie des enchères“. Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLN070.
Der volle Inhalt der QuelleThe common thread of this manuscript is the study of some of the main automatic decision processes using data provided by either strategic or non-strategic agents. In the first part of the manuscript, we study the learning of revenue-maximizing auctions on data provided by the bidders. We first introduce this framework by a detailed overview of the classical results of the auction literature. We prove that if one bidder is aware that his bid distribution is used in order to optimize the seller's revenue, he can take advantage of this data-driven mechanism and increase his utility. To do so, we introduce a simple and generic variational approach to design novel bidding strategies. This strategy works with general value distributions, with asymmetric bidders and for different revenue-maximizing mechanisms. Furthermore, it can be made robust to sample approximation errors on the seller part. This results in a large increase in utility for bidders whether they have a full or partial knowledge of their competitors. This approach naturally yields itself to numerical optimization and algorithms for designing the strategies. We show that these algorithms can be extended to tackle more complicated setups such as the multi-item setting, where no analytical solutions are known. We also study the economical consequences of the existence of such shading strategies on recent results on collusion in revenue-maximizing auctions. This represents a new contribution to the recent line of research at the frontier of game theory, economics and statistics showing how the use of modern statistical learning algorithms on the large amount of data available on internet platforms modifies classical economics interactions.In the second part of the manuscript, we study practical decisions processes enabling to take informed decisions when data are provided by non-strategic agents. We focus on the A/B testing setting where an agent needs to choose between two alternatives. We introduce a new algorithm interpolating between two classical objectives of the multi-armed bandit literature: regret minimization and best-arm identification. Finally, we study some of the main counterfactual estimators used by practitioners when they have access to randomized data. We provide a large overview of most of these estimators, exhibit some of their theoretical properties, their interest in practice and some of their main limitations. This second part provides a large overview of practical statistical tools that can be be used in modern industrial applications
Toupin, Marie-Hélène. „La copule khi-carré et son utilisation en statistique spatiale et pour la modélisation de données multidimensionnelles“. Doctoral thesis, Université Laval, 2017. http://hdl.handle.net/20.500.11794/27977.
Der volle Inhalt der QuelleThis thesis studies the properties of the family of chi-square copulas. This is a generalization of the multidimensional normal copulas obtained by squaring the components of normal random vector. These copulas are indexed by a correlation matrix and by a shape parameter. This thesis shows how this family can be used to perform spatial interpolation and to model multidimensional data. First, the usefulness of this class of dependence structures is demonstrated with an application in spatial statistics. An important problem in that context is to predict the value of a stationary random field at a position where it has not been observed. This thesis shows how to construct such predictions using spatial models based on copulas. One focusses on the use of the family of chi-square copulas in that context. One must first assumes that the correlation matrix has a standard parametric form, such as that of Matérn, indexed by an unknown parameter associated with the force of the spatial association. This parameter is first estimated using a composite pseudo-likelihood constructed from the bivariate distributions of the observed data. Then, a spatial interpolation method using the ranks of the observations is suggested to approximate the best prediction of the random field at an unobserved position under a chi-square copula. In a second work, the fundamental properties of the chi-square copulas are studied in detail. This family allows a lot of flexibility to model multidimensional data. In the bivariate case, this family is adapted to symmetric and asymmetric dependence structures. In larger dimensions, the shape parameter controls the degree of radial asymmetry of the two-dimensional marginal distributions. Parameter estimation procedures of the correlation matrix and of the shape parameter are compared under independent and identically distributed repetitions. Finally, the formulas of the conditional expectation for the best prediction in a spatial context are established. Goodness-of-fit tests for the family of chi-square copulas are then developed. These new tests can be applied to data in any dimension. These procedures are based on two association measures based on the ranks of the observations, which avoids having to specify the marginal distributions. It is shown that the joint behavior of these two measures is asymptotically normal. The efficiency of the new goodness-of-fit procedures is demonstrated through a simulation study and is compared to a classical goodness-of-fit test based on the empirical copula.
Petit, Jean-Claude. „Contribution à l'étude des statistiques non paramétriques : Existence et caractérisation d'évènements libres relativement à une famille de lois de probabilité et applications“. Nancy 1, 1988. http://www.theses.fr/1988NAN10054.
Der volle Inhalt der QuelleCollignon, Olivier. „Recherche statistique de biomarqueurs du cancer et de l'allergie à l'arachide“. Phd thesis, Nancy 1, 2009. http://tel.archives-ouvertes.fr/tel-00430177.
Der volle Inhalt der QuelleBordes, Laurent. „Inférence statistique pour des modèles paramétriques et semi-paramétriques : modèles de l'exponentielle multiple, test du Chi-deux, modèles de vie accélérée“. Bordeaux 1, 1996. http://www.theses.fr/1996BOR10649.
Der volle Inhalt der QuelleAguila, André. „Contribution à la conception d'un planificateur de test : prise en compte des contraintes de testabilité“. Montpellier 2, 1991. http://www.theses.fr/1991MON20289.
Der volle Inhalt der QuelleNguyen, Hoai phuong. „Certification de l'intégrité d'images numériques et de l'authenticité“. Thesis, Reims, 2019. http://www.theses.fr/2019REIMS007/document.
Der volle Inhalt der QuelleNowadays, with the advent of the Internet, the falsification of digital media such as digital images and video is a security issue that cannot be ignored. It is of vital importance to certify the conformity and the integrity of these media. This project, which is in the domain of digital forensics, is proposed to answer this problematic
Sayyareh, Abdolreza. „Test of fit and model selection based on likelihood function“. Phd thesis, AgroParisTech, 2007. http://pastel.archives-ouvertes.fr/pastel-00003400.
Der volle Inhalt der QuelleFayon, Gaëtan. „Modélisation statistique de la diversité multi-site aux fréquences comprises entre 20 et 50 GHz“. Thesis, Toulouse 3, 2017. http://www.theses.fr/2017TOU30284/document.
Der volle Inhalt der QuelleDue to the congestion of standard frequency bands (S, C, Ku bands) and the need to offer higher data rates for multimedia services, space communication systems require to be operated at carrier frequencies higher than 20 GHz: Ka-band (20-30 GHz) for user links or Q/V band (40-50 GHz) for feeder links, to reach the Tb/s capacity. However, these frequency bands are submitted to increase tropospheric impairments, in particular rain attenuation which is its major contributor. In this context, the only use of standard fade mitigation techniques (up-link power control and/or adaptive coding and modulation) is not enough to counteract these propagation impairments and the use of gateways in site diversity configurations allows satisfying link budget to be maintained, relying on redundant gateways to reroute data traffic depending on local meteorological conditions. If several models suited to design such systems already exist, their parameterization is based on a limited number of sub-representative experimental data, both in terms of duration and climatic regions: experimental propagation data in a site diversity context have been often measured in temperate regions (Europe and North America) and represent few years of data (only one year in the majority of the cases). As a consequence, the parameterization, and so the validation, of such models is compromised. This PhD thesis proposes the definition of a new model, the WRF-EMM model, allowing rain attenuation time series and statistics to be generated over a grid of 100 x 100 km2, coupling the high resolution weather prediction model WRF (Weather Research and Forecasting) with the EMM (ElectroMagnetic Module), especially optimized during this thesis. Outputs of this simulator can feed site diversity models in order to design future satellite communications systems. At mid-latitudes, the results are promising and the use of the WRF-EMM model to generate site diversity synthetic datasets and to parameterize site diversity models wherever in the world should now be envisaged as an alternative to experimental data. In parallel with the development of the WRF-EMM model, this thesis also proposes the introduction of a new testing metric allowing to integrate the inter- annual variabilities during the validation process of statistical models, which has not been the case until now