Multiple testing

Results

• (2012) Gilles Blanchard, Sylvain Delattre, Étienne Roquain. Testing over a continuum of null hypotheses. Under minor revision.
• (2012) Gilles Blanchard, Torsten Dickhaus, Étienne Roquain, Fanny Villers. On least favorable configurations for step-up-down tests. Under minor revision.
• (2012) Pierre Neuvial, Étienne Roquain. On false discovery rate thresholding for classification under sparsity. Under revision.
• (2011) Étienne Roquain. Type I error rate control in multiple testing: a survey with proofs. Journal de la Société Française de Statistique, 152(2):3--38.   [Hal]   [arXiv]
• (2011) Étienne Roquain and Fanny Villers. Exact calculations for false discovery proportion with application to least favorable configurations. Annals of Statistics Volume 39, Number 1, 2011, 584-612.   [Projet Euclid]   [arXiv]
• (2010) Kyung In Kim, Etienne Roquain and Mark A. van de Wiel. Spatial Clustering of Array CGH Features in Combination with Hierarchical Multiple Testing. Statistical Applications in Genetics and Molecular Biology, Vol. 9, No. 1, 2010.   [journal]   [arXiv]
• (2010) Alain Celisse and Stéphane Robin. A cross-validation based estimation of the proportion of true null hypotheses. J. Statist. Planning Inference, 2010 (electronic). Volume 140, Issue 11, November 2010, Pages 3132-3147. DOI:10.1016/j.jspi.2010.04.014 .   [journal]   [arXiv]

Related papers

• (2011) Sylvain Delattre, Étienne Roquain. On the false discovery proportion convergence under Gaussian equi-correlation. Statistics and Probability Letters, 81(1): 111--115.   [journal]
• (2008) Gilles Blanchard and Etienne Roquain. Two simple sufficient conditions for FDR control. Electronic Journal of Statistics. 2 963-992.
  
  
• (2009) Gilles Blanchard and Etienne Roquain. Adaptive FDR control under independence and dependence. To appear in Journal of Machine Learning Research.
  
  
• (2009) Clayton Scott, Gowtham Bellala and Rebecca Willett. The false discovery rate for statistical pattern recognition. Electronic Journal of Statistics. 3 651-677.
  
  
• (2009) Gilles Blanchard and Clayton Scott. Novelty detection: Unlabeled data definitely help. Appearing in Proceedings of the 12th on Artificial Intelligence and Statistics (AISTATS).
  
  

Past meetings

• July, 2nd, 2012: closing meeting of the project, with the following talks:
  • Étienne Roquain: On fdr thresholding for classification under sparsity (joint work with Pierre Neuvial)
• June, 14th, 2012: Hypothesis Testing and Bayesian Inference: New Applications of Kernel Methods by Arthur Gretton (Gatsby Neuroscience Unit and University College London)
• December, 3rd, 2010: testing problems and computer vision
• November, 16th, 2009: Exact calculation of false discovery rate for step-up and step-down procedures by Étienne Roquain and Fanny Villers   [preprint]