Nesta tese apresentam-se desenvolvimentos metodológicos para analisar dados com omissão e também estudos delineados para compreender os resultados de tais análises. Escrutinam-se análises de sensibilidade bayesiana e clássica para dados com respostas categorizadas sujeitas a omissão. Mostra-se que as componentes subjetivas de cada abordagem podem influenciar os resultados de maneira não-trivial, independentemente do tamanho da amostra, e que, portanto, as conclusões devem ser cuidadosamente avaliadas. Especificamente, demonstra-se que distribuições \\apriori\\ comumente consideradas como não-informativas ou levemente informativas podem, na verdade, ser bastante informativas para parâmetros inidentificáveis, e que a escolha do modelo sobreparametrizado também tem um papel importante. Quando há omissão em variáveis explicativas, também é necessário propor um modelo marginal para as covariáveis mesmo se houver interesse apenas no modelo condicional. A especificação incorreta do modelo para as covariáveis ou do modelo para o mecanismo de omissão leva a inferências enviesadas para o modelo de interesse. Trabalhos anteriormente publicados têm-se dividido em duas vertentes: ou utilizam distribuições semiparamétricas/não-paramétricas, flexíveis para as covariáveis, e identificam o modelo com a suposição de um mecanismo de omissão não-informativa, ou empregam distribuições paramétricas para as covariáveis e permitem um mecanismo mais geral, de omissão informativa. Neste trabalho analisam-se respostas binárias, combinando um mecanismo de omissão informativa com um modelo não-paramétrico para as covariáveis contínuas, por meio de uma mistura induzida pela distribuição \\apriori\\ de processo de Dirichlet. No caso em que o interesse recai apenas em momentos da distribuição das respostas, propõe-se uma nova análise de sensibilidade sob o enfoque clássico para respostas incompletas que evita suposições distribucionais e utiliza parâmetros de sensibilidade de fácil interpretação. O procedimento tem, em particular, grande apelo na análise de dados contínuos, campo que tradicionalmente emprega suposições de normalidade e/ou utiliza parâmetros de sensibilidade de difícil interpretação. Todas as análises são ilustradas com conjuntos de dados reais. / We present methodological developments to conduct analyses with missing data and also studies designed to understand the results of such analyses. We examine Bayesian and classical sensitivity analyses for data with missing categorical responses and show that the subjective components of each approach can influence results in non-trivial ways, irrespectively of the sample size, concluding that they need to be carefully evaluated. Specifically, we show that prior distributions commonly regarded as slightly informative or non-informative may actually be too informative for non-identifiable parameters, and that the choice of over-parameterized models may drastically impact the results. When there is missingness in explanatory variables, we also need to consider a marginal model for the covariates even if the interest lies only on the conditional model. An incorrect specification of either the model for the covariates or of the model for the missingness mechanism leads to biased inferences for the parameters of interest. Previously published works are commonly divided into two streams: either they use semi-/non-parametric flexible distributions for the covariates and identify the model via a non-informative missingness mechanism, or they employ parametric distributions for the covariates and allow a more general informative missingness mechanism. We consider the analysis of binary responses, combining an informative missingness model with a non-parametric model for the continuous covariates via a Dirichlet process mixture. When the interest lies only in moments of the response distribution, we consider a new classical sensitivity analysis for incomplete responses that avoids distributional assumptions and employs easily interpreted sensitivity parameters. The procedure is particularly useful for analyses of missing continuous data, an area where normality is traditionally assumed and/or relies on hard-to-interpret sensitivity parameters. We illustrate all analyses with real data sets.

La stratégie de l’Union Européenne pour atteindre les objectifs climatiques, est d’augmenter progressivement la part d’énergies renouvelables dans le mix énergétique et d’utiliser l’énergie plus efficacement de la production à la consommation finale. Cela implique de mesurer les performances énergétiques du bâtiment et des systèmes associés, indépendamment des conditions climatiques et de l’usage, pour fournir des solutions efficaces et adaptées de rénovation. Cela implique également de connaître la demande énergétique pour anticiper la production et le stockage d’énergie (mécanismes de demande et réponse). L’estimation des besoins énergétiques et des performances énergétiques des bâtiments ont un verrou scientifique commun : l’identification expérimentale d’un modèle physique du comportement intrinsèque du bâtiment. Les modèles boîte grise, déterminés d’après des lois physiques et les modèles boîte noire, déterminés heuristiquement, peuvent représenter un même système physique. Des relations entre les paramètres physiques et heuristiques existent si la structure de la boîte noire est choisie de sorte qu’elle corresponde à la structure physique. Pour trouver la meilleure représentation, nous proposons d’utiliser, des simulations de Monte Carlo pour analyser la propagation des erreurs dans les différentes transformations de modèle et, une méthode de priorisation pour classer l’influence des paramètres. Les résultats obtenus indiquent qu’il est préférable d’identifier les paramètres physiques. Néanmoins, les informations physiques, déterminées depuis l’estimation des paramètres, sont fiables si la structure est inversible et si la quantité d’information dans les données est suffisante. Nous montrons comment une structure de modèle identifiable peut être choisie, notamment grâce au profil de vraisemblance. L’identification expérimentale comporte trois phases : la sélection, la calibration et la validation du modèle. Ces trois phases sont détaillées dans le cas d’une expérimentation d’une maison réelle en utilisant une approche fréquentiste et Bayésienne. Plus précisément, nous proposons une méthode efficace de calibration Bayésienne pour estimer la distribution postérieure des paramètres et ainsi réaliser des simulations en tenant compte de toute les incertitudes, ce qui représente un atout pour le contrôle prédictif. Nous avons également étudié les capacités des méthodes séquentielles de Monte Carlo pour estimer simultanément les états et les paramètres d’un système. Une adaptation de la méthode de prédiction d’erreur récursive, dans une stratégie séquentielle de Monte Carlo, est proposée et comparée à une méthode de la littérature. Les méthodes séquentielles peuvent être utilisées pour identifier un premier modèle et fournir des informations sur la structure du modèle sélectionnée pendant que les données sont collectées. Par la suite, le modèle peut être amélioré si besoin, en utilisant le jeu de données et une méthode itérative. / The European Union strategy for achieving the climate targets, is to progressively increase the share of renewable energy in the energy mix and to use the energy more efficiently from production to final consumption. It requires to measure the energy performance of buildings and associated systems, independently of weather conditions and user behavior, to provide efficient and adapted retrofitting solutions. It also requires to known the energy demand to anticipate the energy production and storage (demand response). The estimation of building energy demand and the estimation of energy performance of buildings have a common scientific: the experimental identification of the physical model of the building’s intrinsic behavior. Grey box models, determined from first principles, and black box models, determined heuristically, can describe the same physical process. Relations between the physical and mathematical parameters exist if the black box structure is chosen such that it matches the physical ones. To find the best model representation, we propose to use, Monte Carlo simulations for analyzing the propagation of errors in the different model transformations, and factor prioritization, for ranking the parameters according to their influence. The obtained results show that identifying the parameters on the state-space representation is a better choice. Nonetheless, physical information determined from the estimated parameters, are reliable if the model structure is invertible and the data are informative enough. We show how an identifiable model structure can be chosen, especially thanks to profile likelihood. Experimental identification consists of three phases: model selection, identification and validation. These three phases are detailed on a real house experiment by using a frequentist and Bayesian framework. More specifically, we proposed an efficient Bayesian calibration to estimate the parameter posterior distributions, which allows to simulate by taking all the uncertainties into account, which is suitable for model predictive control. We have also studied the capabilities of sequential Monte Carlo methods for estimating simultaneously the states and parameters. An adaptation of the recursive prediction error method into a sequential Monte Carlo framework, is proposed and compared to a method from the literature. Sequential methods can be used to provide a first model fit and insights on the selected model structure while the data are collected. Afterwards, the first model fit can be refined if necessary, by using iterative methods with the batch of data.

Nesta tese apresentam-se desenvolvimentos metodológicos para analisar dados com omissão e também estudos delineados para compreender os resultados de tais análises. Escrutinam-se análises de sensibilidade bayesiana e clássica para dados com respostas categorizadas sujeitas a omissão. Mostra-se que as componentes subjetivas de cada abordagem podem influenciar os resultados de maneira não-trivial, independentemente do tamanho da amostra, e que, portanto, as conclusões devem ser cuidadosamente avaliadas. Especificamente, demonstra-se que distribuições \\apriori\\ comumente consideradas como não-informativas ou levemente informativas podem, na verdade, ser bastante informativas para parâmetros inidentificáveis, e que a escolha do modelo sobreparametrizado também tem um papel importante. Quando há omissão em variáveis explicativas, também é necessário propor um modelo marginal para as covariáveis mesmo se houver interesse apenas no modelo condicional. A especificação incorreta do modelo para as covariáveis ou do modelo para o mecanismo de omissão leva a inferências enviesadas para o modelo de interesse. Trabalhos anteriormente publicados têm-se dividido em duas vertentes: ou utilizam distribuições semiparamétricas/não-paramétricas, flexíveis para as covariáveis, e identificam o modelo com a suposição de um mecanismo de omissão não-informativa, ou empregam distribuições paramétricas para as covariáveis e permitem um mecanismo mais geral, de omissão informativa. Neste trabalho analisam-se respostas binárias, combinando um mecanismo de omissão informativa com um modelo não-paramétrico para as covariáveis contínuas, por meio de uma mistura induzida pela distribuição \\apriori\\ de processo de Dirichlet. No caso em que o interesse recai apenas em momentos da distribuição das respostas, propõe-se uma nova análise de sensibilidade sob o enfoque clássico para respostas incompletas que evita suposições distribucionais e utiliza parâmetros de sensibilidade de fácil interpretação. O procedimento tem, em particular, grande apelo na análise de dados contínuos, campo que tradicionalmente emprega suposições de normalidade e/ou utiliza parâmetros de sensibilidade de difícil interpretação. Todas as análises são ilustradas com conjuntos de dados reais. / We present methodological developments to conduct analyses with missing data and also studies designed to understand the results of such analyses. We examine Bayesian and classical sensitivity analyses for data with missing categorical responses and show that the subjective components of each approach can influence results in non-trivial ways, irrespectively of the sample size, concluding that they need to be carefully evaluated. Specifically, we show that prior distributions commonly regarded as slightly informative or non-informative may actually be too informative for non-identifiable parameters, and that the choice of over-parameterized models may drastically impact the results. When there is missingness in explanatory variables, we also need to consider a marginal model for the covariates even if the interest lies only on the conditional model. An incorrect specification of either the model for the covariates or of the model for the missingness mechanism leads to biased inferences for the parameters of interest. Previously published works are commonly divided into two streams: either they use semi-/non-parametric flexible distributions for the covariates and identify the model via a non-informative missingness mechanism, or they employ parametric distributions for the covariates and allow a more general informative missingness mechanism. We consider the analysis of binary responses, combining an informative missingness model with a non-parametric model for the continuous covariates via a Dirichlet process mixture. When the interest lies only in moments of the response distribution, we consider a new classical sensitivity analysis for incomplete responses that avoids distributional assumptions and employs easily interpreted sensitivity parameters. The procedure is particularly useful for analyses of missing continuous data, an area where normality is traditionally assumed and/or relies on hard-to-interpret sensitivity parameters. We illustrate all analyses with real data sets.

La modélisation par équations structurelles est très répandue dans des domaines très variés et nous l'appliquons pour la première fois en métrologie dans le traitement de données de comparaisons interlaboratoires. Les modèles à équations structurelles à variables latentes sont des modèles multivariés utilisés pour modéliser des relations de causalité entre des variables observées (les données). Le modèle s'applique dans le cas où les données peuvent être regroupées dans des blocs disjoints où chaque bloc définit un concept modélisé par une variable latente. La structure de corrélation des variables observées est ainsi résumée dans la structure de corrélation des variables latentes. Nous proposons une approche bayésienne des modèles à équations structurelles centrée sur l'analyse de la matrice de corrélation des variables latentes. Nous appliquons une expansion paramétrique à la matrice de corrélation des variables latentes afin de surmonter l'indétermination de l'échelle des variables latentes et d'améliorer la convergence de l'algorithme de Gibbs utilisé. La puissance de l'approche structurelle nous permet de proposer une modélisation riche et flexible des biais de mesure qui vient enrichir le calcul de la valeur de consensus et de son incertitude associée dans un cadre entièrement bayésien. Sous certaines hypothèses l'approche permet de manière innovante de calculer les contributions des variables de biais au biais des laboratoires. Plus généralement nous proposons un cadre bayésien pour l'amélioration de la qualité des mesures. Nous illustrons et montrons l'intérêt d'une modélisation structurelle des biais de mesure sur des comparaisons interlaboratoires en environnement. / Structural equation modelling is a widespread approach in a variety of domains and is first applied here to interlaboratory comparisons in metrology. Structural Equation Models with latent variables (SEM) are multivariate models used to model causality relationships in observed variables (the data). It is assumed that data can be grouped into separate blocks each describing a latent concept modelled by a latent variable. The correlation structure of the observed variables is transferred into the correlation structure of the latent variables. A Bayesian approach of SEM is proposed based on the analysis of the correlation matrix of latent variables using parameter expansion to overcome identifiability issues and improving the convergence of the Gibbs sampler. SEM is used as a powerful and flexible tool to model measurement bias with the aim of improving the reliability of the consensus value and its associated uncertainty in a fully Bayesian framework. The approach also allows to compute the contributions of the observed variables to the bias of the laboratories, under additional hypotheses. More generally a global Bayesian framework is proposed to improve the quality of measurements. The approach is illustrated on the structural equation modelling of measurement bias in interlaboratory comparisons in environment.

La modélisation par équations structurelles est très répandue dans des domaines très variés et nous l'appliquons pour la première fois en métrologie dans le traitement de données de comparaisons interlaboratoires. Les modèles à équations structurelles à variables latentes sont des modèles multivariés utilisés pour modéliser des relations de causalité entre des variables observées (les données). Le modèle s'applique dans le cas où les données peuvent être regroupées dans des blocs disjoints où chaque bloc définit un concept modélisé par une variable latente. La structure de corrélation des variables observées est ainsi résumée dans la structure de corrélation des variables latentes. Nous proposons une approche bayésienne des modèles à équations structurelles centrée sur l'analyse de la matrice de corrélation des variables latentes. Nous appliquons une expansion paramétrique à la matrice de corrélation des variables latentes afin de surmonter l'indétermination de l'échelle des variables latentes et d'améliorer la convergence de l'algorithme de Gibbs utilisé. La puissance de l'approche structurelle nous permet de proposer une modélisation riche et flexible des biais de mesure qui vient enrichir le calcul de la valeur de consensus et de son incertitude associée dans un cadre entièrement bayésien. Sous certaines hypothèses l'approche permet de manière innovante de calculer les contributions des variables de biais au biais des laboratoires. Plus généralement nous proposons un cadre bayésien pour l'amélioration de la qualité des mesures. Nous illustrons et montrons l'intérêt d'une modélisation structurelle des biais de mesure sur des comparaisons interlaboratoires en environnement. / Structural equation modelling is a widespread approach in a variety of domains and is first applied here to interlaboratory comparisons in metrology. Structural Equation Models with latent variables (SEM) are multivariate models used to model causality relationships in observed variables (the data). It is assumed that data can be grouped into separate blocks each describing a latent concept modelled by a latent variable. The correlation structure of the observed variables is transferred into the correlation structure of the latent variables. A Bayesian approach of SEM is proposed based on the analysis of the correlation matrix of latent variables using parameter expansion to overcome identifiability issues and improving the convergence of the Gibbs sampler. SEM is used as a powerful and flexible tool to model measurement bias with the aim of improving the reliability of the consensus value and its associated uncertainty in a fully Bayesian framework. The approach also allows to compute the contributions of the observed variables to the bias of the laboratories, under additional hypotheses. More generally a global Bayesian framework is proposed to improve the quality of measurements. The approach is illustrated on the structural equation modelling of measurement bias in interlaboratory comparisons in environment.

Network reconstruction is the process of recovering a unique structured representation of some dynamic system using input-output data and some additional knowledge about the structure of the system. Many network reconstruction algorithms have been proposed in recent years, most dealing with the reconstruction of strictly proper networks (i.e., networks that require delays in all dynamics between measured variables). However, no reconstruction technique presently exists capable of recovering both the structure and dynamics of networks where links are proper (delays in dynamics are not required) and not necessarily strictly proper.The ultimate objective of this dissertation is to develop algorithms capable of reconstructing proper networks, and this objective will be addressed in three parts. The first part lays the foundation for the theory of mathematical representations of proper networks, including an exposition on when such networks are well-posed (i.e., physically realizable). The second part studies the notions of abstractions of a network, which are other networks that preserve certain properties of the original network but contain less structural information. As such, abstractions require less a priori information to reconstruct from data than the original network, which allows previously-unsolvable problems to become solvable. The third part addresses our original objective and presents reconstruction algorithms to recover proper networks in both the time domain and in the frequency domain.

Hochdurchsatzverfahren quantifizieren eine Vielzahl zellulärer Komponenten, können aber selten deren Interaktionen beschreiben. Daher wurden in den letzten 20 Jahren verschiedenste Netzwerk-Rekonstruktionsmethoden entwickelt. Insbesondere Perturbationsdaten erlauben dabei Rückschlüsse über funktionelle Mechanismen in der Genregulierung, Signal Transduktion, intra-zellulärer Kommunikation und anderen Prozessen zu ziehen. Dennoch bleibt Netzwerkinferenz ein ungelöstes Problem, weil die meisten Methoden auf ungeeigneten Annahmen basieren und die Identifizierbarkeit von Netzwerkkanten nicht aufklären. Diesbezüglich beschreibt diese Dissertation eine neue Rekonstruktionsmethode, die auf einfachen Annahmen von Perturbationsausbreitung basiert. Damit ist sie in verschiedensten Zusammenhängen anwendbar und übertrifft andere Methoden in Standard-Benchmarks. Für MAPK und PI3K Signalwege in einer Adenokarzinom-Zellline generiert sie plausible Netzwerkhypothesen, die unterschiedliche Sensitivitäten von PI3K-Mutanten gegenüber verschiedener Inhibitoren überzeugend erklären. Weiterhin wird gezeigt, dass sich Netzwerk-Identifizierbarkeit durch ein intuitives Max-Flow Problem beschreiben lässt. Dieses analytische Resultat erlaubt effektive, identifizierbare Netzwerke zu ermitteln und das experimentelle Design aufwändiger Perturbationsexperimente zu optimieren. Umfangreiche Tests zeigen, dass der Ansatz im Vergleich zu zufällig generierten Perturbationssequenzen die Anzahl der für volle Identifizierbarkeit notwendigen Perturbationen auf unter ein Drittel senkt. Schließlich beschreibt die Dissertation eine mathematische Weiterentwicklung der Modular Response Analysis. Es wird gezeigt, dass sich das Problem als analytisch lösbare orthogonale Regression approximieren lässt. Dies erlaubt eine drastische Reduzierung des nummerischen Aufwands, womit sich deutlich größere Netzwerke rekonstruieren und neueste Hochdurchsatz-Perturbationsdaten auswerten lassen. / 'Omics' technologies provide extensive quantifications of components of biological systems but rarely characterize the interactions between them. To fill this gap, various network reconstruction methods have been developed over the past twenty years. Using perturbation data, these methods can deduce functional mechanisms in gene regulation, signal transduction, intra-cellular communication and many other cellular processes. Nevertheless, this reverse engineering problem remains essentially unsolved because inferred networks are often based on inapt assumptions, lack interpretability as well as a rigorous description of identifiability. To overcome these shortcoming, this thesis first presents a novel inference method which is based on a simple response logic. The underlying assumptions are so mild that the approach is suitable for a wide range of applications while also outperforming existing methods in standard benchmark data sets. For MAPK and PI3K signalling pathways in an adenocarcinoma cell line, it derived plausible network hypotheses, which explain distinct sensitivities of PI3K mutants to targeted inhibitors. Second, an intuitive maximum-flow problem is shown to describe identifiability of network interactions. This analytical result allows to devise identifiable effective network models in underdetermined settings and to optimize the design of costly perturbation experiments. Benchmarked on a database of human pathways, full network identifiability is obtained with less than a third of the perturbations that are needed in random experimental designs. Finally, the thesis presents mathematical advances within Modular Response Analysis (MRA), which is a popular framework to quantify network interaction strengths. It is shown that MRA can be approximated as an analytically solvable total least squares problem. This insight drastically reduces computational complexity, which allows to model much bigger networks and to handle novel large-scale perturbation data.