Statistics of High-Dimensional Time Series
Description
The course provides an overview of statistical methods used for the analysis of high-dimensional time series. Topics include: the dynamic semiparametric factor model, statistics of multivariate time series models, non-parametric and flexible time series estimation, variable selection and empirical pricing kernel estimation. Discussed methods are suitable to mitigate current research challenges on financial markets. The objectives of financial applications thus include the modelling and the forecasting of high-dimensional time series.
The list of literature will be given at the beginning of the course and an active participation is required. Students who are interested in learning and applying statistical methods on financial markets are very welcomed.
Content
1. Introduction
2. Models: Dynamic semiparametric factor model, statistics of multivariate time series
3. Techniques: Non-parametric and flexible time series estimation, variable selection, pricing kernel estimation
4. Applications
Course requirements
Oral exam (70%), presentation (30%)