Valderio Reisen (Université Fédérale d'Espírito Santo), invited professor by the DATAIA Institute at CentraleSupélec, is leading the DATAIA seminar of February 27, on « An overview in factor modelling for high-dimensional time series. Application to air quality and respiratory diseases variables ».
Factor analysis makes use of the eigenvalues and eigenvectors of a symmetric matrix for the purpose of space dimension reduction and forecasting, among others.
This talk considers factor modeling for high-dimensional time series in the presence of atypical observations. Estimation and inference of the number of factor will be addressed in the context of classical and robust methodologies. Some real examples will be discussed with a special attention to : (1) Dimension-reduction of the space generated by multivariate pollutant time series variables, and (2 ) The multi-pollutant effect in respiratory healths to quantify the relation between multi-pollutants and respiratory diseases. In this context, alternative time series regression models will be proposed using multivariate statistic techniques.
Valderio Reisen holds a Master's degree in Statistics from the University of Campinas (Brazil) and a PhD in Mathematics from the University of Manchester Institute of Science and Technology (UK). He is Professor of Statistics at the Federal University of Espírito Santo (Brazil).
His research area is the time series analysis and modelling (long memory models, volatility, robustness, regression, counting processes, space-time models), with applications in environmental engineering (pollution data) and economics (financial data).
The seminar will take place on February 27 2020 from 14.00 to 15.00 at CentraleSupélec - Bâtiment Eiffel - Amphi IV
It will be followed by a coffee break.
Registration free but mandatory within the limit of available seats.
For security reasons, no access to the conference room for unregistered participants.