Dissertations / Theses on the topic 'Modèles paramétriques (statistique)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Modèles paramétriques (statistique).'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Liquet, Benoit. "Sélection de modèles semi-paramétriques." Bordeaux 2, 2002. http://www.theses.fr/2002BOR20958.
Full textTadj, Amel. "Sur les modèles non paramétriques conditionnels en statistique fonctionnelle." Toulouse 3, 2011. http://thesesups.ups-tlse.fr/1219/.
Full textIn this thesis, we consider the problem of the nonparametric estimation in the conditional models when the regressor takes its values in infinite dimension space. More precisely, we treated two cases when the response variable is real and functional. One establishes almost complete uniform convergence of nonparametric estimators for certain conditional models. Firstly, we consider a sequence of i. I. D. Observations. In this context, we build kernel estimators of the conditional cumulative distribution, the conditional density, the conditional hazard function and the conditional mode. We give the uniform consistency rate of these estimators. We illustrate our results by giving an application on simulated samples. Secondly, we generalize our results when the response variable is in a Banach space. We estimate the regression function. In this context, we treat both cases : i. I. D and dependent observations. In the last case, we consider that the observations are Béta-mixing and we establishes almost complete pointwise convergence. Our asymptotic results exploit the topological structure of functional space for the observations. Let us note that all the rates of convergence are based on an hypothesis of concentration of the measure of probability of the functional variable on the small balls and also on the Kolmogorov’s entropy which measures the number of the balls necessary to cover some set. Moreover, when the response variable is functional the rate of convergence contains a new term which depends on type of Banach space
Ngatchou, Wandji Joseph. "Etude de tests paramétriques et non-paramétriques asymptotiquement puissants pour les modèles autorégressifs bilinéaires." Paris 13, 1995. http://www.theses.fr/1995PA132009.
Full textBordes, 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.
Full textBoissières, Henri-Pierre. "Modèles de représentation non paramétriques des fonctions de corrélation des champs stochastiques." Châtenay-Malabry, Ecole centrale de Paris, 1992. http://www.theses.fr/1992ECAP0256.
Full textNguyen, ThiMongNgoc. "Estimation récursive pour des modèles semi-paramétriques." Thesis, Bordeaux 1, 2010. http://www.theses.fr/2010BOR14107/document.
Full textEl, Waled Khalil. "Estimations paramétriques et non-paramétriques pour des modèles de diffusions périodiques." Thesis, Rennes 2, 2015. http://www.theses.fr/2015REN20042/document.
Full textIn this thesis, we consider a drift estimation problem of a certain class of stochastic periodic processes when the length of observation goes to infinity. Firstly, we deal with the linear periodic signal plus noise model dζt = f (t, θ)dt + σ(t)dWt, ;and we study the parametric estimation from a continuous and discrete observation of the process f_tg throughout the interval [0; T]. Using the maximum likelihood method we show the existence of an estimator θˆT which is consistent, asymptotically normal and asymptotically efficient in the sens minimax. When f(t; _) = _f(t), the expression of ^_T is explicit and we obtain the mean square convergence in the both continuous and discrete observation cases. In addition, we deduce the strong consistency in the case of continuous observation.Secondly, we consider the nonparametric estimation problem of the function f(_) for the next two periodic models of type signal plus noise and Ornstein-Uhlenbeckd_t = f(t)dt + _(t)dWt; d_t = f(t)_tdt + dWt:For the signal plus noise model, we build a kernel estimator, the convergence in mean square uniformly over [0; P] and almost sure convergence are established, as well as the asymptotic normality. For the Ornstein-Uhlenbeck model, we prove the convergence uniformly over [0; P] of the bias and the mean square convergence. Moreover, we study the speed of these convergences
Lehéricy, Luc. "Estimation adaptative pour les modèles de Markov cachés non paramétriques." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS550/document.
Full textDuring my PhD, I have been interested in theoretical properties of nonparametric hidden Markov models. Nonparametric models avoid the loss of performance coming from an inappropriate choice of parametrization, hence a recent interest in applications. In a first part, I have been interested in estimating the number of hidden states. I introduce two consistent estimators: the first one is based on a penalized least squares criterion, and the second one on a spectral method. Once the order is known, it is possible to estimate the other parameters. In a second part, I consider two adaptive estimators of the emission distributions. Adaptivity means that their rate of convergence adapts to the regularity of the target distribution. Contrary to existing methods, these estimators adapt to the regularity of each distribution instead of only the worst regularity. The third part is focussed on the misspecified setting, that is when the observations may not come from a hidden Markov model. I control of the prediction error of the maximum likelihood estimator when the true distribution satisfies general forgetting and mixing assumptions. Finally, I introduce a nonhomogeneous variant of hidden Markov models : hidden Markov models with trends, and show that the maximum likelihood estimators of such models is consistent
Laksaci, Ali. "Contribution aux modèles non paramétriques conditionnels pour variables explicatives fonctionnelles." Toulouse 3, 2005. http://www.theses.fr/2005TOU30158.
Full textIn this thesis, we study the problem of a nonparametric modelization when the data are curves. Indeed, we consider real random variable (named response variable) noted Y, and a functional variable (explanatory variable) noted X. The nonparametric model used to study the relation between X and Y is the conditional distribution function noted F which has a density f. Both F and f are supposed to belong to some suitable functional spaces. Firstly, we consider a sequence of i. I. D observations. In this context, we build kernel estimators of the conditional distribution function, the conditional density and its sucessive derivatives. We establish the almost complete convergence rate of these estimators. We use these results in order to study the conditional mode and the conditional quantiles and we give also the almost complete convergence rate of their estimators. Secondly , we suppose that the observations are strongly mixing and we focus on the estimate of the conditional mode. We quantify the asymptotic properties of this estimator, by giving the convergence rate. This result can be used to the prediction problem in functional time series. Our study highlights the phenomenon of concentration properties on small balls of the probability measure of the functional variable. More precisely, these ideas are used to give a statistical solution to curse of dimension and to generalize to infinite dimension many asymptotic results existing in the multivariate case. Moreover, by using recent results in the probability theory of small balls we can see that our results include many time continuous processes. .
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.
Full textVernet, Elodie Edith. "Modèles de mélange et de Markov caché non-paramétriques : propriétés asymptotiques de la loi a posteriori et efficacité." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLS418/document.
Full textLatent models have been widely used in diverse fields such as speech recognition, genomics, econometrics. Because parametric modeling of emission distributions, that is the distributions of an observation given the latent state, may lead to poor results in practice, in particular for clustering purposes, recent interest in using non parametric latent models appeared in applications. Yet little thoughts have been given to theory in this framework. During my PhD I have been interested in the asymptotic behaviour of estimators (in the frequentist case) and the posterior distribution (in the Bayesian case) in two particuliar non parametric latent models: hidden Markov models and mixture models. I have first studied the concentration of the posterior distribution in non parametric hidden Markov models. More precisely, I have considered posterior consistency and posterior concentration rates. Finally, I have been interested in efficient estimation of the mixture parameter in semi parametric mixture models
Lefieux, Vincent. "Modèles semi-paramétriques appliqués à la prévision des séries temporelles : cas de la consommation d’électricité." Phd thesis, Rennes 2, 2007. https://theses.hal.science/tel-00179866/fr/.
Full textRéseau de Transport d’Electricité (RTE), in charge of operating the French electric transportation grid, needs an accurate forecast of the power consumption in order to operate it correctly. The forecasts used everyday result from a model combining a nonlinear parametric regression and a SARIMA model. In order to obtain an adaptive forecasting model, nonparametric forecasting methods have already been tested without real success. In particular, it is known that a nonparametric predictor behaves badly with a great number of explanatory variables, what is commonly called the curse of dimensionality. Recently, semiparametric methods which improve the pure nonparametric approach have been proposed to estimate a regression function. Based on the concept of ”dimension reduction”, one those methods (called MAVE : Moving Average -conditional- Variance Estimate) can apply to time series. We study empirically its effectiveness to predict the future values of an autoregressive time series. We then adapt this method, from a practical point of view, to forecast power consumption. We propose a partially linear semiparametric model, based on the MAVE method, which allows to take into account simultaneously the autoregressive aspect of the problem and the exogenous variables. The proposed estimation procedure is practicaly efficient
Amegble, Koami Dzigbodi. "Tests non paramétriques de spécification pour densité conditionnelle : application à des modèles de choix discret." Master's thesis, Université Laval, 2015. http://hdl.handle.net/20.500.11794/25773.
Full textDans ce travail, nous étudions la performance statistique (taille et puissance) en échantillon fini de deux tests non paramétriques de spécification pour densité conditionnelle proposés par Fan et al. (2006) et Li et Racine (2013). Ces tests permettent de vérifier si les probabilités conditionnelles postulées dans les modèles de choix discret (logit/probit multinomial à effets fixes ou aléatoires, estimateur de Klein et Spady (1993), etc) représentent correctement les choix observés. Par rapport aux tests existants, cette approche a l’avantage d’offrir une forme fonctionnelle flexible alternative au modèle paramétrique lorsque ce dernier se révèle mal spécifié. Ce modèle alternatif est directement issu de la procédure de test et il correspond au modèle non contraint obtenu par des produits de noyaux continus et discrets. Les deux tests explorés ont une puissance en échantillon fini supérieure aux tests existants. Cette performance accrue s’obtient en combinant une procédure bootstrap et l’utilisation de paramètres de lissage des fonctions noyaux par validation croisée par les moindres carrés. Dans notre application, nous parallélisons les calculs de taille et de puissance, ainsi que l’estimation des fenêtres de lissage, sur un serveur multi-processeurs (Colosse, de Calcul Québec). Nous utilisons des routines "Open MPI" pré-implémentées dans R. Par rapport aux simulations effectuées dans les articles originaux, nous postulons des modèles plus proches de ceux habituellement utilisés dans la recherche appliquée (logit et probit à variance unitaire notamment). Les résultats des simulations confirment les bonnes taille et puissance des tests en échantillon fini. Par contre, les gains additionnels de puissance de la statistique lissée proposée par Li et Racine (2013) se révèlent négligeables dans nos simulations. Mots clés : Bootstrap, choix discret, densité conditionnelle, Monte Carlo, produit de noyaux, puissance, taille.
Hernandez, Quintero Angelica. "Inférence statistique basée sur les processus empiriques dans des modèles semi-paramétriques de durées de vie." Toulouse 3, 2010. http://thesesups.ups-tlse.fr/1201/.
Full textSurvival data arise from disciplines such as medicine, criminology, finance and engineering amongst others. In many circumstances the event of interest can be classified in several causes of death or failure and in some others the event can only be observed for a proportion of "susceptibles". Data for these two cases are known as competing risks and long-term survivors, respectively. Issues relevant to the analysis of these two types of data include basic properties such as the parameters estimation, existence, consistency and asymptotic normality of the estimators, and their efficiency when they follow a semiparametric structure. The present thesis investigates these properties in well established semiparametric formulations for the analysis of both competing risks and long-term survivors. It presents an overview of mathematical tools that allow for the study of these basic properties and describes how the modern theory of empirical processes and the theory of semiparametric efficiency facilitate relevant proofs. Also, consistent variance estimate for both the parametric and semiparametric components for the two models are presented. The findings of this research provide the theoretical basis for obtaining inferences with large samples, the calculation of confidence bands and hypothesis testing. The methods are illustrated with data bases generated through simulations
Rakotomarolahy, Patrick. "Méthodes non paramétriques : estimation, analyse et applications aux cycles économiques." Paris 1, 2011. http://www.theses.fr/2011PA010045.
Full textLhéritier, Hugo. "Comportement asymptotique de certains estimateurs sur des modèles paramétriques et sous des conditions non standard." Orléans, 2003. http://www.theses.fr/2003ORLE2005.
Full textNguyen, Van Hanh. "Modèles de mélange semi-paramétriques et applications aux tests multiples." Phd thesis, Université Paris Sud - Paris XI, 2013. http://tel.archives-ouvertes.fr/tel-00987035.
Full textDucasse, Alain. "Estimation de sous-harmoniques à l'aide de méthodes paramétriques." Toulouse, INPT, 1997. http://www.theses.fr/1997INPT016H.
Full textLöser, Kevin. "Apprentissage non-supervisé de la morphologie des langues à l’aide de modèles bayésiens non-paramétriques." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS203/document.
Full textA crucial issue in statistical natural language processing is the issue of sparsity, namely the fact that in a given learning corpus, most linguistic events have low occurrence frequencies, and that an infinite number of structures allowed by a language will not be observed in the corpus. Neural models have already contributed to solving this issue by inferring continuous word representations. These continuous representations allow to structure the lexicon by inducing semantic or syntactic similarity between words. However, current neural models only partially solve the sparsity issue, due to the fact that they require a vectorial representation for every word in the lexicon, but are unable to infer sensible representations for unseen words. This issue is especially present in morphologically rich languages, where word formation processes yield a proliferation of possible word forms, and little overlap between the lexicon observed during model training, and the lexicon encountered during its use. Today, several languages are used on the Web besides English, and engineering translation systems that can handle morphologies that are very different from western European languages has become a major stake. The goal of this thesis is to develop new statistical models that are able to infer in an unsupervised fashion the word formation processes underlying an observed lexicon, in order to produce morphological analyses of new unseen word forms
Top, Alioune. "Estimation paramétriques et tests d'hypothèses pour des modèles avec plusieurs ruptures d'un processus de poisson." Thesis, Le Mans, 2016. http://www.theses.fr/2016LEMA1014/document.
Full textThis work is devoted to the parametric estimation, hypothesis testing and goodnessof-fit test problems for non homogenous Poisson processes. First we consider two models having two jumps located by an unknown parameter.For the first model the sum of jumps is positive. The second is a model of switching intensity, piecewise constant and the sum of jumps is zero. Thus, for each model, we studied the asymptotic properties of the Bayesian estimator (BE) andthe likelihood estimator (MLE). The consistency, the convergence in distribution and the convergence of moments are shown. In particular we show that the BE is asymptotically efficient. For the second model we also consider the problem of asimple hypothesis testing against a one- sided alternative. The asymptotic properties (choice of the threshold and power) of Wald test (WT) and the generalized likelihood ratio test (GRLT) are described.For the proofs we use the method of Ibragimov and Khasminskii. This method is based on the weak convergence of the normalized likelihood ratio in the Skorohod space under some tightness criterion of the corresponding families of measure.By numerical simulations, the limiting variances of estimators allows us to conclude that the BE outperforms the MLE. In the situation where the sum of jumps is zero, we developed a numerical approach to obtain the MLE.Then we consider the problem of construction of goodness-of-test for a model with scale parameter. We show that the Cram´er-von Mises type test is asymptotically parameter-free. It is also consistent
Decurninge, Alexis. "Quantiles univariés et multivariés, approches probabilistes et statistiques : applications radar." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066028/document.
Full textThe description and the estimation of univariate and multivariate models whose underlyingdistribution is heavy-tailed is a strategic challenge. L-moments have becomeclassical tools alternative to central moments for the description of dispersion, skewnessand kurtosis of a univariate heavy-tailed distribution. Indeed, contrary to correspondingcentral moments, they are well defined since the expectation of the distribution of interestis finite. L-moments can be seen as projections of the quantile function on a family oforthogonal polynomials. First, we will estimate parameters of semi-parametric modelsdefined by constraints on L-moments through divergence methods.We will then propose a generalization of L-moments for multivariate distributions using amultivariate quantile function defined as a transport of the uniform distribution on [0; 1]dand the distribution of interest. As their univariate versions, these multivariate L-momentsare adapted for the study of heavy-tailed distributions. We explicitly give their formulationsfor models with rotational parameters.Finally, we propose M-estimators of the scatter matrix of complex elliptical distributions.The family of these distributions form a multivariate semi-parametric model especiallycontaining heavy-tailed distributions. Specific M-estimators adapted to complex ellipticaldistribution with an additional assumption of stationarity are proposed. Performancesand robustness of introduced estimators are studied.Ground and sea clutters are often modelized by complex elliptical distributions in the fieldof radar processing. We illustrate performances of detectors built from estimators of thescatter matrix through proposed methods for different radar scenarios
Naulet, Zacharie. "Développement d'un modèle particulaire pour la régression indirecte non paramétrique." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLED057/document.
Full textThis dissertation deals with Bayesian nonparametric statistics, in particular nonparametric mixture models. The manuscript is divided into a general introduction and three parts on rather different aspects of mixtures approaches (sampling, asymptotic, inverse problem). In mixture models, the parameter to infer from the data is a function. We set a prior distribution on an abstract space of functions through a stochastic integral of a kernel with respect to a random measure. Usually, mixture models were used primilary in probability density function estimation problems. One of the contributions of the present manuscript is to use them in regression problems.In this context, we are essentially concerned with the following problems :- Sampling of the posterior distribution- Asymptotic properties of the posterior distribution- Inverse problems, in particular the estimation of the Wigner distribution from Quantum Homodyne Tomography measurements
Fraysse, Philippe. "Estimation récursive dans certains modèles de déformation." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2013. http://tel.archives-ouvertes.fr/tel-00844393.
Full textHaultfoeuille, Xavier d'. "Essai sur quelques problèmes d'identification en économie." Paris 1, 2009. https://pastel.archives-ouvertes.fr/tel-00402960.
Full textGneyou, Kossi Essona. "Inférence statistique non paramétrique pour l'analyse du taux de panne en fiabilité : Théorèmes limites fonctionnels pour les processus produit-limite et les estimateurs non paramétriques du taux de panne dans les modèles de variables aléatoires arbitrairement censurées." Paris 6, 1991. http://www.theses.fr/1991PA066504.
Full textSow, Mohamedou. "Développement de modèles non paramétriques et robustes : application à l’analyse du comportement de bivalves et à l’analyse de liaison génétique." Thesis, Bordeaux 1, 2011. http://www.theses.fr/2011BOR14257/document.
Full textThe development of robust and nonparametric approaches for the analysis and statistical treatment of high-dimensional data sets exhibiting high variability, as seen in the environmental and genetic fields, is instrumental. Here, we model complex biological data with application to the analysis of bivalves’ behavior and to linkage analysis. The application of mathematics to the analysis of mollusk bivalves’behavior gave us the possibility to quantify and translate mathematically the animals’behavior in situ, in close or far field. We proposed a nonparametric regression model and compared three nonparametric estimators (recursive or not) of the regressionfunction to optimize the best estimator. We then characterized the biological rhythms, formalized the states of opening, proposed methods able to discriminate the behaviors, used shot-noise analysis to characterize various opening/closing transitory states and developed an original approach for measuring online growth.In genetics, we proposed a more general framework of robust statistics for linkage analysis. We developed estimators robust to distribution assumptions and the presence of outlier observations. We also used a statistical approach where the dependence between random variables is specified through copula theory. Our main results showed the practical interest of these estimators on real data for QTL and eQTL analysis
Gannaz, Irène. "Estimation par ondelettes dans les modèles partiellement linéaires." Phd thesis, Université Joseph Fourier (Grenoble), 2007. http://tel.archives-ouvertes.fr/tel-00197146.
Full textGuin, Ophélie. "Méthodes bayésiennes semi-paramétriques d'extraction et de sélection de variables dans le cadre de la dendroclimatologie." Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00636704.
Full textLopez, Olivier. "Réduction de dimension en présence de données censurées." Phd thesis, Rennes 1, 2007. http://tel.archives-ouvertes.fr/tel-00195261.
Full textvariable explicative. Nous développons une nouvelle approche de réduction de la dimension afin de résoudre ce problème.
Arkoun, Ouerdia. "Estimation non paramétrique pour les modèles autorégressifs." Phd thesis, Université de Rouen, 2009. http://tel.archives-ouvertes.fr/tel-00464024.
Full textNguyen, Thi Mong Ngoc. "Estimation récursive pour les modèles semi-paramétriques." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2010. http://tel.archives-ouvertes.fr/tel-00938607.
Full textTran, Xuan Quang. "Les modèles de régression dynamique et leurs applications en analyse de survie et fiabilité." Thesis, Bordeaux, 2014. http://www.theses.fr/2014BORD0147/document.
Full textThis thesis was designed to explore the dynamic regression models, assessing the sta-tistical inference for the survival and reliability data analysis. These dynamic regressionmodels that we have been considered including the parametric proportional hazards andaccelerated failure time models contain the possibly time-dependent covariates. We dis-cussed the following problems in this thesis.At first, we presented a generalized chi-squared test statisticsY2nthat is a convenient tofit the survival and reliability data analysis in presence of three cases: complete, censoredand censored with covariates. We described in detail the theory and the mechanism to usedofY2ntest statistic in the survival and reliability data analysis. Next, we considered theflexible parametric models, evaluating the statistical significance of them by usingY2nandlog-likelihood test statistics. These parametric models include the accelerated failure time(AFT) and a proportional hazards (PH) models based on the Hypertabastic distribution.These two models are proposed to investigate the distribution of the survival and reliabilitydata in comparison with some other parametric models. The simulation studies were de-signed, to demonstrate the asymptotically normally distributed of the maximum likelihood estimators of Hypertabastic’s parameter, to validate of the asymptotically property of Y2n test statistic for Hypertabastic distribution when the right censoring probability equal 0% and 20%.n the last chapter, we applied those two parametric models above to three scenes ofthe real-life data. The first one was done the data set given by Freireich et al. on thecomparison of two treatment groups with additional information about log white blood cellcount, to test the ability of a therapy to prolong the remission times of the acute leukemiapatients. It showed that Hypertabastic AFT model is an accurate model for this dataset.The second one was done on the brain tumour study with malignant glioma patients, givenby Sauerbrei & Schumacher. It showed that the best model is Hypertabastic PH onadding five significance covariates. The third application was done on the data set given by Semenova & Bitukov on the survival times of the multiple myeloma patients. We did not propose an exactly model for this dataset. Because of that was an existing oneintersection of survival times. We, therefore, suggest fitting other dynamic model as SimpleCross-Effect model for this dataset
Khadraoui, Lobna. "Sélection de copules archimédiennes dans un modèle semi-paramétrique." Master's thesis, Université Laval, 2018. http://hdl.handle.net/20.500.11794/30251.
Full textThis work considers a semi-parametric linear model with error terms modeled by a copula chosen from the Archimedean family or the normal copula. The modeling of errors by a copula provides flexibility and makes it possible to characterize the dependency structure in a simple and effective manner. The simplicity lies in the fact that a single parameter α controls the degree of dependency present in the data. The efficiency is in the fact that this semi-parametric model weakens standard assumptions often encountered in applied statistics namely normality and independence. After an implementation of the model based on a copula we proposed a theoretical study on the asymptotic behavior of the estimator of the dependence parameter α by showing its consistency and its asymptotic normality under classical assumptions of regularity. Estimation of the model parameters is performed by maximizing a pseudo-likelihood. The selection of the best copula that fits the data for each case is based on the Akaike selection criterion. A comparison with the criterion of cross-validation is presented as well. Finally, a numerical study on simulated and real data sets is proposed.
Loubaton, Rodolphe. "Modélisation des effets d’une intervention dans un programme génique temporel." Electronic Thesis or Diss., Université de Lorraine, 2023. http://www.theses.fr/2023LORR0322.
Full textCancer cells can exhibit abnormalities in the expression of certain genes that alter the normal functioning of cellular programs, causing them to proliferate uncontrollably. These cellular programs are made up of the expression of thousands of genes that activate and interact in a concerted fashion. These interactions can be represented as a gene regulatory network. The general objective of this thesis, which follows on from the work of Vallat et al (2021), is to model a cellular program using temporal gene expression data. The model constructed will make it possible to identify target genes whose reduced expression could reduce cell proliferation for therapeutic purposes. In the first chapter, we review existing gene network models in order to justify the choice of our model, which is detailed in the second chapter. This model (called the LiRE model) is a Gaussian parametric statistical model that allows us to take into account gene expression dynamics using parameters describing, among other things, the interactions between genes. The various theoretical properties of our model have enabled us to develop an iterative algorithm for inferring parameters, combining steps of penalized linear regressions lasso and regressions with positivity constraints and constraints on the sum of coefficients. In this chapter, we also carry out a numerical study of this model to investigate its performance on simulated data. In the third chapter, we describe methods for modeling and predicting the results of biological intervention experiments modifying the expression of certain genes, in order to predict the best target genes whose expression should be decreased in the cellular program to reduce cancer cell proliferation. We give theoretical results on different models including our LiRE model. In the final chapter, we detail our R package MultiRNAflow, which enabled us to perform statistical analyses of dynamic and complex gene expression data in order to characterize the genes selected for inference in our model LiRE
Arlot, Sylvain. "Rééchantillonnage et Sélection de modèles." Phd thesis, Université Paris Sud - Paris XI, 2007. http://tel.archives-ouvertes.fr/tel-00198803.
Full textLa 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.
Roget-Vial, Céline. "deux contributions à l'étude semi-paramétrique d'un modèle de régression." Phd thesis, Université Rennes 1, 2003. http://tel.archives-ouvertes.fr/tel-00008730.
Full textRuggiero, Michèle. "Analyse semi-paramétrique des modèles de durées : l'apport des méthodes bayésiennes." Aix-Marseille 2, 1989. http://www.theses.fr/1989AIX24008.
Full textWe propose a semiparametric analysis of duration models. In this special class of regression models, the dependant variable is the time spent by a person in a particular state - the duration of an unemployment spell for instance - and the explanatory variables are the personal characteristics of this person. The semiparametric analysis of these models consists in specifying the relation between the duration and the explanatory variables (duration is supposed to be a specified function of the explanatory variables, depending on a finite number of unknown parameters) without specifying the data distribution. The parameters involved in this relation are then considered as parameters of interest, and the data distribution is a nuisance parameter. The thesis begins with a survey of nonbayesian semiparametric methods of estimation; it seems that these methods fail in discarding the nuisance data distribution. We then suggest a bayesian method, the principle of which is to give a prior distribution on the nuisance parameter - the data distribution. We then get semiparametric estimators for the parameters of interest, by computing their posterior distribution, conditional on the data and integrated with respect to the nuisance parameter. The thesis ends with a simulation, to check the robustness of the estimators we propose
Pchelintsev, Evgeny. "Estimation paramétrique améliorée pour des modèles régressifs observés sous un bruit avec sauts." Rouen, 2012. http://www.theses.fr/2012ROUES041.
Full textThis thesis is devoted to parametric estimation for discret and continuous time regression models which are conditionally Gaussian with respect to a non-observable process. We consider the problem of estimating the unknown parameter using data governed by regression models. We develop improved methods for parameter estimation of regression models compared to least squares estimates. For regression models with Levy noise and Ornstein -- Uhlenbeck noise, we obtain explicit formulas for the minimal gain in mean square accuracy when using shrinkage estimates instead of the least squares estimates. For continuous models, are built improved estimates of the parameters on discrete data. For the model with noise and with jumps, we establish the asymptotic minimaxity of the least squares estimates and of the proposed shrinkage estimates in the sense of robust risk. We also carry on a simulation study of the proposed estimation procedures
Kiessé, Tristan Senga. "Approche non-paramétrique par noyaux associés discrets des données de dénombrement." Pau, 2008. https://tel.archives-ouvertes.fr/tel-00372180.
Full textThis work introduces a new nonparametric approach by discrete associatedkernels for count data. First, we define the discrete kernel associated to a discrete probability distribution and we examine its basical properties. Furthermore, we construct the discrete associated-kernel estimator which is the analog of some one in the continuous case of the last decade. We investigate their properties ; in particular, we show the pointwise convergence of the estimator in the sense of mean squared error. The choice of bandwidth is mainly done through cross-validation and excess of zeros. For illustrating, we study some discrete probability distributions such that Poisson, binomial, negative binomial, that we consider as associated-kernels. Thus, we need to improve it by introducing a new discrete probability distribution, called triangular, in order to serve as symmetric associated-kernel. The discrete associated-kernel method is then used for a semiparametric estimation of count distributions and, also, for nonparametric regression on a count explanatory variable. This discrete associated-kernel method is illustrated through simulations and real examples of count data. For a sample size not so large, the importance and the performance of discrete associated-kernels are pointed out compared with the Dirac type kernel and, sometimes, the continuous ones
Guilloux, Agathe. "Inférence non paramétrique en statistique des durées de vie sous biais de sélection." Rennes 1, 2004. http://www.theses.fr/2004REN10058.
Full textMorsli, Nadia. "Inférence non paramétrique pour les modèles Gibbsiens de processus ponctuels spatiaux." Thesis, Grenoble, 2014. http://www.theses.fr/2014GRENM055/document.
Full textAmong models allowing to introduce interaction between points, we find the large class of Gibbs models coming from statistical physics. Such models can produce repulsive as well as attractive point pattern. In this thesis, we are interested in the semi-parametric inference of such models characterized by the Papangelou conditional intensity. Two frameworks are considered. First, we describe a procédure which intends to estimate the first-order interaction term (also called Poisson intensity) of the Papangelou conditional intensity. Under the assumption of finite range of the process, the idea upon which the procedure is based allows us to neglect higher-order interaction terms. We study the stong consistency and the asymptotic normality and conduct a simulation study which highlights the efficiency of the method for finite observation window. Second, we focus on the main class of Gibbs models which is the class of pairwise interaction point processes. We construct a kernel-based estimator of the pairwise interaction function. Two cases are studied: the stationary case and the isotropic case.The estimators, we propose, exploit the finite range property and the estimator of the Poisson intensity defined in the first part. We present asymptotic properties, namely the strong consistency, the behavior of the mean squared error and the asymptotic normality
Olivier, Adelaïde. "Analyse statistique des modèles de croissance-fragmentation." Thesis, Paris 9, 2015. http://www.theses.fr/2015PA090047/document.
Full textThis work is concerned with growth-fragmentation models, implemented for investigating the growth of a population of cells which divide according to an unknown splitting rate, depending on a structuring variable – age and size being the two paradigmatic examples. The mathematical framework includes statistics of processes, nonparametric estimations and analysis of partial differential equations. The three objectives of this work are the following : get a nonparametric estimate of the division rate (as a function of age or size) for different observation schemes (genealogical or continuous) ; to study the transmission of a biological feature from one cell to an other and study the feature of one typical cell ; to compare different populations of cells through their Malthus parameter, which governs the global growth (when introducing variability in the growth rate among cells for instance)
Mohdeb, Zaher. "Tests d'hypothèses linéaires dans un modèle de régression non paramétrique." Versailles-St Quentin en Yvelines, 1999. http://www.theses.fr/1999VERS0003.
Full textLerasle, Matthieu. "Rééchantillonnage et sélection de modèles optimale pour l'estimation de la densité." Toulouse, INSA, 2009. http://eprint.insa-toulouse.fr/archive/00000290/.
Full textEzzahrioui, M'hamed. "Prévision dans les modèles conditionels en dimension finie." Littoral, 2007. http://www.theses.fr/2007DUNK0187.
Full textThis thesis is dedicated to the survey of the asymptotic properties of conditional functional parameters in nonparametric statistics, when the explanatory variable takes values in an infinite dimension space. In this nonparametric setting, we consider the estimators of the usual functional parameters, as the conditional law, the conditional probability density, the conditional quantile, the conditional mode and the conditional hazard function, when the explanatory variable is functional. We are mainly interested in the problem of forecasting in non parametric conditional models, when the data are functional random variables. We propose an alternative to the method of regression while using the conditional mode or the conditional median. The survey of our functional estimators deals with i. I. D. As well as strong mixing data for which we generalize the classical finite-dimension results. Forecasting in parametric or nonparametric statistics is one of the most crucial questions to which the statisticians try to give answers for different frameworks. It is worth to note that the usual regression model does not answer to the problem of forecasting in some situations such as asymmetri densities or in the case where the density admits several peaks among which one is sufficiently large. The conditionnal mode/quantile are then alternatives to answer the mentioned problem. This thesis traces itself in the continuity of the existing works in infinite dimension. It develops a lot of aspects of both practical and theorical points of view. Our results are applied to real data (taken from climatology) and to simulated data
Kaid, Zoulikha. "Sur l'estimation non paramétrique des modèles conditionnels pour variables fonctionnelles spatialement dépendantes." Thesis, Lille 3, 2012. http://www.theses.fr/2012LIL30061/document.
Full textThe main purpose of this thesis concerns the problem of spatial prediction using some nonparametric conditional models where the covariate variable is a functional one. More precisely, we treat the nonparametric estimation of the conditional mode and that of the conditional quantiles as spatial prediction tools alternative to the classical spatial regression of real response variable given a functional variable.Concerning the first model, that is the conditional mode, it is estimated by maximizing the spatial version of the kernel estimate of the conditional density. Under a general mixing condition and the concentration properties of the probability measure of the functional variable, we establish the almost complete convergence (with rate), the Lp consistency (with rate) and the asymptotic normality of the considered estimator. The usefulness of this estimation is illustrated by an application on real meteorological data.The model of the conditional quantiles is considered in the second part of this thesis and is treated as the inverse function of the conditional cumulative distribution function which is estimated by a double kernel estimator. Under the same general conditions as in the first model, we give the convergence rate in the Lp- norm and we show the asymptotic normality of the constructed estimator. These asymptotic results are closely related to the concentration properties on small balls of the probability measure of the underlying explanatory variable and the regularity of the conditional cumulative distribution function.Our study generalizes to spatial case some existing results in functional times series case. Finally, we highlight what our models brings compared to classical regression, discussing the use of our results as preliminary works to construct predictive regions
Khardani, Salah. "Prévision non paramétrique dans les modèles de censure via l'estimation du mode conditionnel." Littoral, 2010. http://www.theses.fr/2010DUNK0277.
Full textIn this work, we address the problem of estimating the mode and conditional mode functions, for independent and dependent data, under random censorship. Firstly, we consider an independent and identically distributed (iid) sequence random variables (rvs) {T_i , i [equal to or higher than]1}, with density f. This sequence is right-censored by another iid sequence of rvs {Ci , i[equal to or higher than]1} which is supposed to be independent of {T_i , i [equal to or higher than]1}. We are interested in the regression problem of T given a covariable X. We state convergence and asymptomatic normality of Kernel-based estimators of conditional density and mode. Using the “plug-in” method for the unknown parameters, confidence intervals are gicen. Also simulations are drawn. In a second step we deal with the simple mode, given by par θ = arg max_{t. IR} f (t). Here, the sequence {T_i , i [equal to or higher than]1} is supposed to be stationary and strongly mixing whereas the {Ci , i[equal to or higher than]1} are iid. We build a mode estimator (based on a density kernel estimator) for which we state the almost sure consistency. Finally, we extend the conditional mode consistency results to the case where the {T_i , i [equal to or higher than]1} are strongly mixing
Canaud, Matthieu. "Estimation de paramètres et planification d’expériences adaptée aux problèmes de cinétique - Application à la dépollution des fumées en sortie des moteurs." Thesis, Saint-Etienne, EMSE, 2011. http://www.theses.fr/2011EMSE0619/document.
Full textPhysico-chemical models designed to represent experimental reality may prove to be inadequate. This is the case of nitrogen oxide trap, used as an application support of our thesis, which is a catalyst system treating the emissions of the diesel engine. The outputs are the curves of concentrations of pollutants, which are functional data, depending on scalar initial concentrations.The initial objective of this thesis is to propose experiental design that are meaningful to the user. However, the experimental design relying on models, most of the work has led us to propose a statistical representation taking into account the expert knowledge, and allows to build this plan.Three lines of research were explored. We first considered a non-functional modeling with the use of kriging theory. Then, we took into account the functional dimension of the responses, with the application and extension of varying coefficent models. Finally, starting again from the original model, we developped a model depending on the kinetic parameters of the inputs (scalar) using a nonparametric representation.To compare the methods, it was necessary to conduct an experimental campaign, and we propose an exploratory design approach, based on maximum entropy
Avalos, Marta. "Modèles additifs parcimonieux." Phd thesis, Université de Technologie de Compiègne, 2004. http://tel.archives-ouvertes.fr/tel-00008802.
Full textChimard, Florencia. "Mélanges de processus ponctuels spatio-temporels et approche bayésienne semi-paramétrique." Antilles-Guyane, 2010. http://www.theses.fr/2010AGUY0392.
Full textPoint processes are often used as tools for describing spatial or spatio- temporal point patterns. In this Phd dissertation, we give an overview of bayesian statistical analysis for point processes and recent tools Iike the Dirichlet process and its diverse extensions. We focus on situations where the available data are maps of the studied point process at different observations dates. Two contexts are considered. Firstly, we consider occurrences of events in a studied area forming the realization of a spatio-temporal Cox process directed by a generalized shot noise intensity measure. A hidden Poisson process generates contributions to the intensity measure which are distributed according to a Dirichlet process centered on the Gamma distribution. For data consisting of spatial locations of occurrences between several pairs of consecutive observation dates, we develop statistical inference about the parameters of interest by means of MCMC methods within the framework of hierarchical bayesian modeling. A data augmentation algorithm is introduced and tested on artificial data. Secondly, we analyse the case where the point process support is discrete with at most one occurrence for a given element of the support. For such binary data, we present and discuss models based on Bernoulli distribution mixture with a background intensity following a log-gaussian. The statistical inference for these models is developped by using a hierarchical bayesian approach. Tests are carried out on artificial data and data from Yellow Leaf Sugarcane Virus observations