Contents
Academic literature on the topic 'Inférence causale données'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Inférence causale données.'
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.
Journal articles on the topic "Inférence causale données"
Dupuy, Claire, Ferdinand Teuber, and Virginie Van Ingelgom. "Citizens’ experiences of a policy-ridden environment: A methodological contribution to feedback studies based on qualitative secondary analysis." Bulletin of Sociological Methodology/Bulletin de Méthodologie Sociologique 156, no. 1 (October 2022): 124–57. http://dx.doi.org/10.1177/07591063221132342.
Full textTurcotte, Catherine, Nathalie Prévost, and Pier-Olivier Caron. "Évaluer la compréhension en lecture d’un récit et d’un texte informatif auprès d’élèves de 8 ans." Canadian Journal of Applied Linguistics 26, no. 1 (March 15, 2023): 28–45. http://dx.doi.org/10.37213/cjal.2023.32826.
Full textNicholls, Jim, and J. Kelly Russell. "Igneous Rock Associations 20. Pearce Element Ratio Diagrams: Linking Geochemical Data to Magmatic Processes." Geoscience Canada 43, no. 2 (May 18, 2016): 133. http://dx.doi.org/10.12789/geocanj.2016.43.095.
Full textDissertations / Theses on the topic "Inférence causale données"
Chaisemartin, Clément de. "Essais sur la question de l'inférence causale en sciences humaines." Paris, EHESS, 2012. http://www.theses.fr/2012EHES0172.
Full textIn the first chapter, I show that instrumental variable (IV) estimates have greater internal and external validity than was previously thought. On internal validity, monotonicity is not necessary for the Wald ratio to identify a Local Average Treatrnent Effect. On external validity, IV identify treatment effects among a population G larger than compliers. P(G) is not identified but 1 derive a non-trivial lower bound for it under a fairly credible assumption. The instrumented difference in differences model is identified under two common trend assumptions on the outcome and on the treatment. In the second chapter of this thesis, 1 consider what can be obtained under a common trend assumption on the outcome only. 1 show that when the outcome is bounded, the average treatment effect can be bounded. Ln the fourth chapter, co-authored with Xavier D'Haultfoeuille, we relax the perfect compliance assumption in the Change in Change mode!. We show that treatment effects in a population of compliers are point identified when the treatment rate does not change in the control group, and partially identified otherwise
Sella, Nadir. "Reconstruction de réseaux à partir de données génomiques et cliniques." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS351.
Full textThis thesis consists in the development of a novel methodological approach to reconstruct networks starting from biological and clinical data. It overcomes some technical and computational problems of existing methods to accomplish this task. Our algorithm (MIIC), allows the study of discrete, continuous and mixed datasets with any type of probability and density distributions, including the possible presence of latent variables, which are very important in real contexts where it is not always possible to collect all relevant variables. MIIC is available through a web interface at the address: https://miic.curie.fr, and as an R package available on CRAN. The second part of the thesis is devoted to the analysis of real life applications: from gene regulatory network reconstruction and protein contact map reconstruction, to the study of clinical records of patients affected by cognitive disorders or breast cancer. MIIC can help physicians in visualizing and analysing direct, indirect and possibly causal effects from patient medical records, discovering novel unexpected direct interdependencies between clinically relevant information or explaining a missing connection through other links found in the reconstruction
Girerd, Nicolas. "Apport des méthodes d'inférence causale et de la modélisation additive de survie pour l’évaluation d’un effet thérapeutique dans le domaine spécifique de la cardiologie et de la chirurgie cardiaque." Thesis, Lyon 1, 2014. http://www.theses.fr/2014LYO10329.
Full textClinical trials are difficult to conduct in the field of cardiac surgery. As a consequent, relatively few clinical trials are available in this field and most of the available data is observational. Yet, surgical techniques are very dependent on the patients’ characteristics, which translate into a high amount of attribution bias. We studied the impact of the type of surgical revascularization (complete or incomplete) on long-term survival using a 4/1 propensity score matching. We identified a significant interaction on a relative scale between the type of revascularization and age with regards to long-term all-cause mortality. The treatment effect was weaker in older patients. We then studied the interaction between age and treatment effect on both an additive scale and a relative scale using additive and multiplicative hazard models. We identified a significant submultiplicative interaction whereas we did not identify noteworthy additive interaction. This result indicate that treatment effect is additive in this illustration. We also measured risk differences from the multiplicative hazard model in several age subsets. Risk differences extracted from the multiplicative model were similar in age subsets, which confirmed a constant treatment effect across subsets on an additive scale despite a weaker treatment effect on a multiplicative scale in older patients. Our work encourages an evaluation of treatment effect on both an additive and a relative scale in propensity score based analyses of observational data
Grari, Vincent. "Adversarial mitigation to reduce unwanted biases in machine learning." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS096.
Full textThe past few years have seen a dramatic rise of academic and societal interest in fair machine learning. As a result, significant work has been done to include fairness constraints in the training objective of machine learning algorithms. Its primary purpose is to ensure that model predictions do not depend on any sensitive attribute as gender or race, for example. Although this notion of independence is incontestable in a general context, it can theoretically be defined in many different ways depending on how one sees fairness. As a result, many recent papers tackle this challenge by using their "own" objectives and notions of fairness. Objectives can be categorized in two different families: Individual and Group fairness. This thesis gives an overview of the methodologies applied in these different families in order to encourage good practices. Then, we identify and complete gaps by presenting new metrics and new Fair-ML algorithms that are more appropriate for specific contexts
Bailly, Sébastien. "Utilisation des antifongiques chez le patient non neutropénique en réanimation." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAS013/document.
Full textCandida species are among the main pathogens isolated from patients in intensive care units (ICUs) and are responsible for a serious systemic infection: invasive candidiasis. A late and unreliable diagnosis of invasive candidiasis aggravates the patient's status and increases the risk of short-term death. The current guidelines recommend an early treatment of patients with high risks of invasive candidiasis, even in absence of documented fungal infection. However, increased antifungal drug consumption is correlated with increased costs and the emergence of drug resistance whereas there is yet no consensus about the benefits of the probabilistic antifungal treatment.The present work used modern statistical methods on longitudinal observational data. It investigated the impact of systemic antifungal treatment (SAT) on the distribution of the four Candida species most frequently isolated from ICU patients', their susceptibilities to SATs, the diagnosis of candidemia, and the prognosis of ICU patients. The use of autoregressive integrated moving average (ARIMA) models for time series confirmed the negative impact of SAT use on the susceptibilities of the four Candida species and on their relative distribution over a ten-year period. Hierarchical models for repeated measures showed that SAT has a negative impact on the diagnosis of candidemia: it decreases the rate of positive blood cultures and increases the time to positivity of these cultures. Finally, the use of causal inference models showed that early SAT has no impact on non-neutropenic, non-transplanted patient prognosis and that SAT de-escalation within 5 days after its initiation in critically ill patients is safe and does not influence the prognosis
Monneret, Gilles. "Inférence de réseaux causaux à partir de données interventionnelles." Thesis, Sorbonne université, 2018. http://www.theses.fr/2018SORUS290/document.
Full textThe purpose of this thesis is the use of current transcriptomic data in order to infer a gene regulatory network. These data are often complex, and in particular intervention data may be present. The use of causality theory makes it possible to use these interventions to obtain acyclic causal networks. I question the notion of acyclicity, then based on this theory, I propose several algorithms and / or improvements to current techniques to use this type of data
Cabeli, Vincent. "Learning causal graphs from continuous or mixed datasets of biological or clinical interest." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS331.
Full textThe work in this thesis follows the theory primarily developed by Judea Pearl on causal diagrams; graphical models that allow all causal quantities of interest to be derived formally and intuitively. We address the problem of causal network inference from observational data alone, i.e., without any intervention from the experimenter. In particular, we propose to improve existing methods to make them more suitable for analyzing real-world data, by freeing them as much as possible from constraints on data distributions, and by making them more interpretable. We propose an extension of MIIC, a constraint-based information-theoretic approach to recover the equivalence class of the causal graph from observations. Our contribution is an optimal discretization algorithm based on the minimum description length principle to simultaneously estimate the value of mutual (and multivariate) information and evaluate its significance between samples of variables of any nature: continuous, categorical or mixed. We use these developments to analyze mixed datasets of clinical (medical records of patients with cognitive disorders; or breast cancer and being treated by neoadjuvant chemotherapy) or biological interest (gene regulation networks of hematopoietic stem and precursor cells)
Laanani, Moussa. "Étude des relations entre l’état de santé, sa prise en charge et le décès par suicide à partir du Système national des données de santé Contacts with Health Services During the Year Prior to Suicide Death andPrevalent Conditions A Nationwide Study Collider and Reporting Biases Involved in the Analyses of Cause of Death Associations in Death Certificates: an Illustration with Cancer and Suicide." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASR016.
Full textSuicide is a major public health problem in France, with nearly 10,000 premature deaths each year. Studying the determinants of suicide is complex. It is a multi-factorial phenomenon, which can be influenced by personal and/or environmental, biomedical and/or socio-economic factors. The presence of diseases (psychiatric or physical) in the individual plays an important role. Psychiatric pathologies can be complicated by suicidal processes (suicidal ideation, which may be followed by suicidal behaviour and then death by suicide). For physical diseases, the disease can have a significant impact on the quality of life of the individual, favouring suicidal processes, and thus death by suicide. Psychiatric disorders can thus worsen physical illnesses and be a step towards the occurrence of suicidal processes. Physical diseases can also occur in individuals suffering from psychiatric disorders, and can trigger suicidal processes. For both psychiatric and physical diseases, suicidal processes can also be the consequence of adverse effects of drug treatments. In such cases, it is often difficult to disentangle the role of the treatment and that of the pathology being treated. The aim of this thesis was to study the complex relationships between diseases and suicide death, using data from the French National Health Data System (SNDS)