Impact de la dépendance dans les procédures de tests multiples en grande dimension

Abstract : Motivated by issues raised by the analysis of gene expressions data, this thesis focuses on the impact of dependence on the properties of multiple testing procedures for high-dimensional data. We propose a methodology based on a Factor Analysis model for the correlation structure. Model parameters are estimated thanks to an em algorithm and an ad hoc methodology allowing to determine the model that fits best the covariance structure is defined. Moreover, the factor structure provides a general framework to deal with dependence in multiple testing. Two main issues are more particularly considered : the estimation of the proportion of true null hypotheses, and the control of error rates. The proposed framework leads to less variability in the estimation of both the proportion of true null hypotheses and the number of false-positives. Consequently, it shows large improvements of power and stability of simultaneous inference with respect to existing multiple testing procedures. These results are illustrated by real data from microarray experiments and the proposed methodology is implemented in a R package called FAMT.
Document type :
Complete list of metadatas
Contributor : Chloé Friguet <>
Submitted on : Thursday, November 25, 2010 - 9:13:58 AM
Last modification on : Thursday, November 15, 2018 - 11:56:33 AM
Long-term archiving on : Saturday, February 26, 2011 - 2:41:15 AM


  • HAL Id : tel-00539741, version 1


Chloé Friguet. Impact de la dépendance dans les procédures de tests multiples en grande dimension. Mathématiques [math]. Agrocampus - Ecole nationale supérieure d'agronomie de rennes, 2010. Français. ⟨tel-00539741v1⟩



Record views


Files downloads