**Associate professor in mathematics**

Team : Probability and Statistics

*Contact :*

UFR des Sciences de l’UVSQ

Bâtiment Fermat, bureau 2311

45 avenue des Etats Unis

78035 Versailles cedex

*Tel* : 00 33 1 39 25 46 16

Member of the teaching team of the Master MIASHS

Co-organizer of the probability and statistics seminar of the LMV

Link to the page devoted to the courses I taught (in french)

Curriculum Vitae (french version)

## Research themes

Limit theorems (large and moderate deviation principles), asymptotic statistics, extreme value statistics, empirical likelihood methodology, survival analysis, statistical climatology and hydrology

## Other themes of interest

Limit theorems for martingales, self-normalization, reliability, sequential statistics, multivariate data analysis

## Publications

*Moderate deviations for stable Markov chains and regression models, Electronic Journal of Probability, volume 4, article 8, p.1-28 (1999)**Principes de déviations modérées pour des martingales autonormalisées*, Comptes-Rendus de l’Académie des Sciences, série I, volume 330 (no 10), p. 909-914 (2000)*Moderate deviations for some dependent variables , Part 1 :*martingales, Mathematical Methods of Statistics, Volume 10, number 1 (2001)*Moderate deviations for some dependent variables, Part 2 : some kernel estimators,*Mathematical Methods of Statistics, Volume 10, number 2, pp 161-193 (2001)*Large and moderate deviations upper bounds for the Gaussian autoregressive process”,*Statistics and Probability Letters, Volume 51, Issue 3, pp 235-243 (2001)- (coll. with A.Mokkadem and M.Pelletier)
*Large and moderate deviations principles for kernel estimation of a multivariate density and its partial derivatives*, Australian and New Zealand Journal of Statistics, Volume 47, Issue 4, p.489-502 (2005) - (coll. with A.Mokkadem and M.Pelletier)
*A large deviations upper bound for the kernel mode estimator*, Theory of Probability and its Applications, Volume 50, Issue 1, p.153-165 (2006) - (coll. with R.Worms)
*Estimation of second order parameters using probability weighted moments*, ESAIM : Probability and Statistics, volume 16 (1), pp 97-113 (2012) (link) - (coll. with R.Worms)
*Empirical likelihood based confidence regions for first order parameters of heavy tailed distributions*, Journal of Statistical Planning and Inference, Volume 141, Issue 8, August 2011, Pages 2769-2786 (link) - (coll. with R.Worms)
*A test for comparing tail indices for heavy tailed distributions via empirical likelihood*, Communications in Statistics : Theory and Methods, Volume 44, Pages 3289-3302 (2015, accepted in 2013) (lien) - (coll. with R.Worms)
*New estimators of the extreme value index under random right censoring, for heavy-tailed distributions*, , Extremes, Volume 17, Issue 2, Pages 337-358 (2014) (link) - (coll. with R.Worms)
*A Lynden-Bell integral estimator for extremes of randomly truncated data*, Statistics and Probability Letters, Volume 109, Pages 106-117 (2016) (link ) - (coll. with R.Worms)
*Extreme value statistics for censored data with heavy tails under competing risks*, Metrika, Volume 81, pages 849-889 (2018) (HAL link, ArXiv link, link to the journal website). Supplementary material for this paper downloadable here) - (coll. with J.Beirlant and R.Worms)
*Estimation of the extreme value index in a censorship framework: asymptotic and finite sample behaviour,*Journal of Statistical Planning and Inference, Volume 202, Pages 31-56 (2019) (HAL link , ArXiv link, journal link) - (coll. with R.Worms)
*Weibull-tail coefficient estimation in presence of random censoring*, Extremes, Volume 22(4), Pages 667-704 (2019) (journal link , HAL link)

## Submitted or current works

- (coll. with R.Worms)
*Moment estimators of the extreme value index for randomly censored data in the Weibull domain of attraction*(HAL link ) - (coll. with P.Naveau)
*Record events attribution in climate studies*(2020, submitted ; HAL archive link , R code, manual for the R code) - (coll. with R.Worms)
*Extremes value statistics for heavy-tailed and light-tailed distributions in the presence of censoring*(2020, submitted ; HAL link)

## Other documents

*Moderate deviation principles for martingales, with statistical applications*, PhD of the Marne-la-Vallée University, defended the 21st of january, 2000 , Advisor : Marie Duflo (introduction and short versions of chapters, in french : gzipped postscript)- Introductory guide for the SAS software (link to the pdf file, in french)
- Documentation for basic use of the ETS (Time Series) package for SAS (link to the pdf file, in french)
*The Speedup test : a statistical methodology for program*(collaboration with S.Touati ; statistical contribution in the field of performance optimisation ;

speedup analysis and computation*Journal of Concurrency and Computation : Practice and Experience*, 2013, Vol 25 (10), pp 1410-1426, link)*Parametric and Non-Parametric Statistics for Program Performance Analysis and Comparison*(collaboration with S.Touati ; INRIA Research Report number 8875, march 2016, HAL link )*Modelling Program’s Performance with Gaussian Mixtures for Parametric Statistics*(collaboration with S.Touati), IEEE Transactions on Multi-Scale Computing Systems, Volume 4, Issue 3, 383-395 (2018)

* *

## A selection of some recent talks

- Probability and Statistics Seminar of the Laboratory of Mathematics of Versailles :
*Vraisemblance empirique : concepts et propriétés de base*(6 janvier 2009, slides in french) - Joint Statistics Seminar of the Katholieke Universiteit Leuven (KUL) :
*Estimation of second order parameters using probability weighted moments*(5 mars 2009) - 41st Statistics days of the French Statistical Society, Bordeaux, May 2009 :
*Estimation of the second order parameters of a heavy tailed distribution using probability weighted moments* - Probability and Statistics Seminar of the Laboratory of Mathematics of Versailles :
*Confidence regions for the first order parameters of a heavy tailed distribution using empirical likelihood*(June 7th, 2011) - International meeting of probability and statistics JIPS 2011 (Algiers), invited talk :
*On empirical likelihood methodology and extreme value statistics*(Nov 22, 2011) - Statistics seminar of IRMAR (Rennes) :
*New estimators for the tail index for randomly censored data : framework and empirical results*(June 1st, 2012) - 1st conference of the International Society for Nonparametric Statistics (Chalkidiki/Thessalonic, Greece) :
*About empirical likelihood-based confidence regions in extreme values statistics*(june 2012) - 9th ERCIM conference on CMS (Sevilla) :
*Extreme value index estimation for randomly censored data with competing risks*(December 11th, 2016) - Image-Optimisation-Probability Seminar of the Institute of Mathematics of Bordeaux :
*Extreme Value Statistics for Censored Data*(June 7th, 2018) - 4th Conference of the International Society of Non-Parametric Statistics, Salerno (Italy),
*Extreme value analysis for randomly censored data under competing risks*(June 13th, 2018) - Workgroup Extreme Values and Longevity (VELO), LPSM laboratory (Paris 6 and 7) :
*Asymptotic distribution of some extreme value index estimators under random censoring, and influence of the censoring strength in the tail*(June 29th, 2018) - EVA 2019 conference (Zagreb) :
*Record events attribution in a climate change context*

*Last update : December 7th, 2020*