FranceCountry of destination:
United States of America
When analyzing data, missing values are ubiquitous and can occur for plenty of reasons: machines that fail, individuals who forget to answer some questions in a questionnaire, etc. Missing values are problematic since most statistical methods cannot be applied directly on incomplete data. The aim of the project was the development of new statistical methods (especially dedicated to the exploration and visualization of data) to handle missing values in order to provide users facing this problem with new practical solutions. The fields of application include genetics and food science.
Julie Josse was an associate professor of Statistics between 2011 and 2015 at Agrocampus Ouest in Rennes. During her AgreenSkills fellowship, she has taken benefits of several stays in the Department of Statistics Palo Alto, in Stanford University. She is currently professor of Statistics at the applied math department (CMAP) at Ecole Polytechnique (Saclay) and member of the data-science initiative and XPOP INRIA team, since September 2016. Her main research fields are missing values, visualization with dimensionality reduction (PCA, correspondence analysis), multi-blocks data, low rank matrix estimation, questionnaire analyses. She has specialized in missing data, visualization and the nonparametric analyses of complex data structures. Julie Josse is dedicated to reproducible research with the R software and wrote books and developed many leading packages. She is actively involved in the scientific community and has organized an international conference on missing values.
Holmes S, Josse J, 2017. Discussion of “50 Years of Data Science”, Journal of Computational and Graphical Statistics, 26:4, 768-769.
Josse, J. and Reiter, J. P. 2017-2018. Introduction to the Special Section on Missing Data. Statistical Science.
Sobczyk, P, Bogdan, M. and Josse, J. 2017. PCA using penalized semi-integrated likelihood. Journal of Computational and Graphical Statistics, 26:4, 826-839. Doi: 10.1080/10618600.2017.134030.
Fithian, W. and Josse, J. 2016. Multiple Correspondence Analysis & the Multilogit Bilinear Model. Journal of Multivariate Analysis, 57, 87-102. Doi: 10.1016/j. jmva.2017.02.009
Husson, F., Josse, J. and Saporta, G. 2016. Jan de Leeuw and the French school of data analysis. Journal of Statistical Software, vol. 73(6). Doi: 10.18637/jss.v073. i06.
Josse, J. and Wager, S. 2016. Bootstrap-Based Regularization for Low-Rank Matrix Estimation. Journal of Machine Learning Research, 17(124):129.
Ph.D. dissertation award (Marie-Jeanne Laurent-Duhamel – French Statistical Society), 2012: its aim is to reward the quality of a young, french-speaking statistician’s doctoral thesis. In
2012, it distinguishes a notable contribution to applied statistical research. http://www.sfds.asso.fr/