The linear analysis of the regression, called also more simply linear regression, is one of the most used statistical methods in applied sciences and social sciences. Its objective is double: first of all it consists in describing the relations between a variable, called explained (or dependent) variable, and several variables, called explanatory (or independent) variables. It also makes it possible to conduct forecasts of the explained variable in terms of the explanatory variables. The links between the explanatory variables exert a considerable influence on the effectiveness of the method, whatever the objective in which it is used. We expose in this paper some of the properties of these links, recently proved and published in several pa...
L’analyse des corrélations canoniques est une méthode statistique, proposée en 1936 par Hotelling, s...
In the regression framework, many studies are focused on the high-dimensional problem where the numb...
In this thesis, we consider the usual linear regression model in the case where the error process is...
The linear analysis of the regression, called also more simply linear regression, is one of the most...
International audienceA number of methods are available for deriving a categorization model of type ...
La plupart des analyses statistiques sont construites selon une logique linéaire : analyses de varia...
URL des Documents de travail : http://centredeconomiesorbonne.univ-paris1.fr/bandeau-haut/documents-...
It is well known that standard asymptotic theory is not valid or is extremely unreliable in models w...
International audienceIn large-scale signicance analysis, ignoring dependence or not is a core issue...
Multivariate data are often treated with regression methods on one hand, Geometric Data Analyse me...
The main purpose of this thesis concerns the problem of spatial prediction using some nonparametric ...
This PhD thesis deals with the following statistical problems: Variable selection in high-Dimensiona...
For contingency table, concepts of independence are not so easy to understand in statistical practic...
System identification is a term gathering tools that identify mathematical models from observations....
This thesis takes place within the theories of nonasymptotic statistics and model selection. Its goa...
L’analyse des corrélations canoniques est une méthode statistique, proposée en 1936 par Hotelling, s...
In the regression framework, many studies are focused on the high-dimensional problem where the numb...
In this thesis, we consider the usual linear regression model in the case where the error process is...
The linear analysis of the regression, called also more simply linear regression, is one of the most...
International audienceA number of methods are available for deriving a categorization model of type ...
La plupart des analyses statistiques sont construites selon une logique linéaire : analyses de varia...
URL des Documents de travail : http://centredeconomiesorbonne.univ-paris1.fr/bandeau-haut/documents-...
It is well known that standard asymptotic theory is not valid or is extremely unreliable in models w...
International audienceIn large-scale signicance analysis, ignoring dependence or not is a core issue...
Multivariate data are often treated with regression methods on one hand, Geometric Data Analyse me...
The main purpose of this thesis concerns the problem of spatial prediction using some nonparametric ...
This PhD thesis deals with the following statistical problems: Variable selection in high-Dimensiona...
For contingency table, concepts of independence are not so easy to understand in statistical practic...
System identification is a term gathering tools that identify mathematical models from observations....
This thesis takes place within the theories of nonasymptotic statistics and model selection. Its goa...
L’analyse des corrélations canoniques est une méthode statistique, proposée en 1936 par Hotelling, s...
In the regression framework, many studies are focused on the high-dimensional problem where the numb...
In this thesis, we consider the usual linear regression model in the case where the error process is...