1,721,009 research outputs found
Stability of variable selection in regression and classification issues for correlated data in high dimension
No full textLes données à haut-débit, par leur grande dimension et leur hétérogénéité, ont motivé le développement de méthodes statistiques pour la sélection de variables. En effet, le signal est souvent observé simultanément à plusieurs facteurs de confusion. Les approches de sélection habituelles, construites sous l'hypothèse d'indépendance des variables, sont alors remises en question car elles peuvent conduire à des décisions erronées. L'objectif de cette thèse est de contribuer à l'amélioration des méthodes de sélection de variables pour la régression et la classification supervisée, par une meilleure prise en compte de la dépendance entre les statistiques de sélection. L'ensemble des méthodes proposées s'appuie sur la description de la dépendance entre covariables par un petit nombre de variables latentes. Ce modèle à facteurs suppose que les covariables sont indépendantes conditionnellement à un vecteur de facteurs latents. Une partie de ce travail de thèse porte sur l'analyse de données de potentiels évoqués (ERP). Les ERP sont utilisés pour décrire par électro-encéphalographie l'évolution temporelle de l'activité cérébrale. Sur les courts intervalles de temps durant lesquels les variations d'ERPs peuvent être liées à des conditions expérimentales, le signal psychologique est faible, au regard de la forte variabilité inter-individuelle des courbes ERP. En effet, ces données sont caractérisées par une structure de dépendance temporelle forte et complexe. L'analyse statistique de ces données revient à tester pour chaque instant un lien entre l'activité cérébrale et des conditions expérimentales. Une méthode de décorrélation des statistiques de test est proposée, basée sur la modélisation jointe du signal et de la dépendance à partir d'une connaissance préalable d'instants où le signal est nul. Ensuite, l'apport du modèle à facteurs dans le cadre général de l'Analyse Discriminante Linéaire est étudié. On démontre que la règle linéaire de classification optimale conditionnelle aux facteurs latents est plus performante que la règle non-conditionnelle. Un algorithme de type EM pour l'estimation des paramètres du modèle est proposé. La méthode de décorrélation des données ainsi définie est compatible avec un objectif de prédiction. Enfin, on aborde de manière plus formelle les problématiques de détection et d'identification de signal en situation de dépendance. On s'intéresse plus particulièrement au Higher Criticism (HC), défini sous l'hypothèse d'un signal rare de faible amplitude et sous l'indépendance. Il est montré dans la littérature que cette méthode atteint des bornes théoriques de détection. Les propriétés du HC en situation de dépendance sont étudiées et les bornes de détectabilité et d'estimabilité sont étendues à des situations arbitrairement complexes de dépendance. Dans le cadre de l'identification de signal, une adaptation de la méthode Higher Criticism Thresholding par décorrélation par les innovations est proposée.The analysis of high throughput data has renewed the statistical methodology for feature selection. Such data are both characterized by their high dimension and their heterogeneity, as the true signal and several confusing factors are often observed at the same time. In such a framework, the usual statistical approaches are questioned and can lead to misleading decisions as they are initially designed under independence assumption among variables. The goal of this thesis is to contribute to the improvement of variable selection methods in regression and supervised classification issues, by accounting for the dependence between selection statistics. All the methods proposed in this thesis are based on a factor model of covariates, which assumes that variables are conditionally independent given a vector of latent variables. A part of this thesis focuses on the analysis of event-related potentials data (ERP). ERPs are now widely collected in psychological research to determine the time courses of mental events. In the significant analysis of the relationships between event-related potentials and experimental covariates, the psychological signal is often both rare, since it only occurs on short intervals and weak, regarding the huge between-subject variability of ERP curves. Indeed, this data is characterized by a temporal dependence pattern both strong and complex. Moreover, studying the effect of experimental condition on brain activity for each instant is a multiple testing issue. We propose to decorrelate the test statistics by a joint modeling of the signal and time-dependence among test statistics from a prior knowledge of time points during which the signal is null. Second, an extension of decorrelation methods is proposed in order to handle a variable selection issue in the linear supervised classification models framework. The contribution of factor model assumption in the general framework of Linear Discriminant Analysis is studied. It is shown that the optimal linear classification rule conditionally to these factors is more efficient than the non-conditional rule. Next, an Expectation-Maximization algorithm for the estimation of the model parameters is proposed. This method of data decorrelation is compatible with a prediction purpose. At last, the issues of detection and identification of a signal when features are dependent are addressed more analytically. We focus on the Higher Criticism (HC) procedure, defined under the assumptions of a sparse signal of low amplitude and independence among tests. It is shown in the literature that this method reaches theoretical bounds of detection. Properties of HC under dependence are studied and the bounds of detectability and estimability are extended to arbitrarily complex situations of dependence. Finally, in the context of signal identification, an extension of Higher Criticism Thresholding based on innovations is proposed
Stabilité de la sélection de variables pour la régression et la classification de données corrélées en grande dimension
Full text linkThe analysis of high throughput data has renewed the statistical methodology for feature selection. Such data are both characterized by their high dimension and their heterogeneity, as the true signal and several confusing factors are often observed at the same time. In such a framework, the usual statistical approaches are questioned and can lead to misleading decisions as they are initially designed under independence assumption among variables. The goal of this thesis is to contribute to the improvement of variable selection methods in regression and supervised classification issues, by accounting for the dependence between selection statistics. All the methods proposed in this thesis are based on a factor model of covariates, which assumes that variables are conditionally independent given a vector of latent variables. A part of this thesis focuses on the analysis of event-related potentials data (ERP). ERPs are now widely collected in psychological research to determine the time courses of mental events. In the significant analysis of the relationships between event-related potentials and experimental covariates, the psychological signal is often both rare, since it only occurs on short intervals and weak, regarding the huge between-subject variability of ERP curves. Indeed, this data is characterized by a temporal dependence pattern both strong and complex. Moreover, studying the effect of experimental condition on brain activity for each instant is a multiple testing issue. We propose to decorrelate the test statistics by a joint modeling of the signal and time-dependence among test statistics from a prior knowledge of time points during which the signal is null. Second, an extension of decorrelation methods is proposed in order to handle a variable selection issue in the linear supervised classification models framework. The contribution of factor model assumption in the general framework of Linear Discriminant Analysis is studied. It is shown that the optimal linear classification rule conditionally to these factors is more efficient than the non-conditional rule. Next, an Expectation-Maximization algorithm for the estimation of the model parameters is proposed. This method of data decorrelation is compatible with a prediction purpose. At last, the issues of detection and identification of a signal when features are dependent are addressed more analytically. We focus on the Higher Criticism (HC) procedure, defined under the assumptions of a sparse signal of low amplitude and independence among tests. It is shown in the literature that this method reaches theoretical bounds of detection. Properties of HC under dependence are studied and the bounds of detectability and estimability are extended to arbitrarily complex situations of dependence. Finally, in the context of signal identification, an extension of Higher Criticism Thresholding based on innovations is proposed.Les données à haut-débit, par leur grande dimension et leur hétérogénéité, ont motivé le développement de méthodes statistiques pour la sélection de variables. En effet, le signal est souvent observé simultanément à plusieurs facteurs de confusion. Les approches de sélection habituelles, construites sous l'hypothèse d'indépendance des variables, sont alors remises en question car elles peuvent conduire à des décisions erronées. L'objectif de cette thèse est de contribuer à l'amélioration des méthodes de sélection de variables pour la régression et la classification supervisée, par une meilleure prise en compte de la dépendance entre les statistiques de sélection. L'ensemble des méthodes proposées s'appuie sur la description de la dépendance entre covariables par un petit nombre de variables latentes. Ce modèle à facteurs suppose que les covariables sont indépendantes conditionnellement à un vecteur de facteurs latents. Une partie de ce travail de thèse porte sur l'analyse de données de potentiels évoqués (ERP). Les ERP sont utilisés pour décrire par électro-encéphalographie l'évolution temporelle de l'activité cérébrale. Sur les courts intervalles de temps durant lesquels les variations d'ERPs peuvent être liées à des conditions expérimentales, le signal psychologique est faible, au regard de la forte variabilité inter-individuelle des courbes ERP. En effet, ces données sont caractérisées par une structure de dépendance temporelle forte et complexe. L'analyse statistique de ces données revient à tester pour chaque instant un lien entre l'activité cérébrale et des conditions expérimentales. Une méthode de décorrélation des statistiques de test est proposée, basée sur la modélisation jointe du signal et de la dépendance à partir d'une connaissance préalable d'instants où le signal est nul. Ensuite, l'apport du modèle à facteurs dans le cadre général de l'Analyse Discriminante Linéaire est étudié. On démontre que la règle linéaire de classification optimale conditionnelle aux facteurs latents est plus performante que la règle non-conditionnelle. Un algorithme de type EM pour l'estimation des paramètres du modèle est proposé. La méthode de décorrélation des données ainsi définie est compatible avec un objectif de prédiction. Enfin, on aborde de manière plus formelle les problématiques de détection et d'identification de signal en situation de dépendance. On s'intéresse plus particulièrement au Higher Criticism (HC), défini sous l'hypothèse d'un signal rare de faible amplitude et sous l'indépendance. Il est montré dans la littérature que cette méthode atteint des bornes théoriques de détection. Les propriétés du HC en situation de dépendance sont étudiées et les bornes de détectabilité et d'estimabilité sont étendues à des situations arbitrairement complexes de dépendance. Dans le cadre de l'identification de signal, une adaptation de la méthode Higher Criticism Thresholding par décorrélation par les innovations est proposée
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
Stability of model selection for high-dimensional data
No full textInternational audienceThe analysis of data generated by high throughput technologies such as DNA microarrays has markedly renewed the statistical methodology for multiple testing and feature selection in regression or classification issues. Such data are characterized by both their high-dimension, as the number of measured features is close to several thousands whereas the sample size is about some tens, and their heterogeneity, as the true signal and several confusing factors (uncontrolled and unobserved) are often observed at the same time. In such a framework, the usual statistical approaches are questioned and can lead to misleading decisions for example. Some recent papers (Efron 2007, Leek and Storey 2007 and 2008; Friguet et al, 2009 ) have focused on the negative impact of data heterogeneity on the consistency of the ranking which results from multiple testing procedures. This presentation aims at showing that data heterogeneity also a effects the stability of supervised classification model selection which is often used to identify relevant subsets of features. Key characteristics of selection methods are both classification or prediction performance and reproducibility of the selected variables to perturbation in the data. It is first shown that selected subsets using well-known procedures such as LASSO (Tibshirani, 1996) are subject to a high variability. The stability of this selection method is compared through a simulation study, considering several scenario of dependence between variables: independence, block dependence, factor structure and Toeplitz design (as also considered in Meinshausen and Buhlmann, 2010). Simulation studies show that most usual methods do not select theoretical best predictors and that interesting performances of classification are performed only when a high number of variables are selected. As suggested in Friguet et al. (2009), a supervised factor model is proposed to identify a low-dimensional linear kernel which captures data dependence and new strategies for model selection are deduced. This new strategy is finally shown to improve stability of the usual methods. Indeed, interesting performances of classification are reached for a smaller number of selected variables and best theoretical predictors are more often selected for structures with a high degree of dependence
Stability of model selection for high-dimensional data
No full textInternational audienceThe analysis of data generated by high throughput technologies such as DNA microarrays has markedly renewed the statistical methodology for multiple testing and feature selection in regression or classification issues. Such data are characterized by both their high-dimension, as the number of measured features is close to several thousands whereas the sample size is about some tens, and their heterogeneity, as the true signal and several confusing factors (uncontrolled and unobserved) are often observed at the same time. In such a framework, the usual statistical approaches are questioned and can lead to misleading decisions for example. Some recent papers (Efron 2007, Leek and Storey 2007 and 2008; Friguet et al, 2009 ) have focused on the negative impact of data heterogeneity on the consistency of the ranking which results from multiple testing procedures. This presentation aims at showing that data heterogeneity also a effects the stability of supervised classification model selection which is often used to identify relevant subsets of features. Key characteristics of selection methods are both classification or prediction performance and reproducibility of the selected variables to perturbation in the data. It is first shown that selected subsets using well-known procedures such as LASSO (Tibshirani, 1996) are subject to a high variability. The stability of this selection method is compared through a simulation study, considering several scenario of dependence between variables: independence, block dependence, factor structure and Toeplitz design (as also considered in Meinshausen and Buhlmann, 2010). Simulation studies show that most usual methods do not select theoretical best predictors and that interesting performances of classification are performed only when a high number of variables are selected. As suggested in Friguet et al. (2009), a supervised factor model is proposed to identify a low-dimensional linear kernel which captures data dependence and new strategies for model selection are deduced. This new strategy is finally shown to improve stability of the usual methods. Indeed, interesting performances of classification are reached for a smaller number of selected variables and best theoretical predictors are more often selected for structures with a high degree of dependence
- …
