Statistics Econometrics and Time Series Analysis: Regression analysis (ordinary least squares, regression diagnostics, and inference) Basic time series concepts (stationarity, autocorrelation, ARMA/ARIMA models) Programming and Data Analysis

The course provides students with a deep foundation in statistical and time series methods tailored to the analysis of financial data. It combines traditional models, such GARCH, stochastic volatility and heterogeneous autoregressive models, with modern forecasting techniques that incorporate machine learning, addressing the unique challenges of financial markets such as volatility clustering, leverage effects, and heavy tails. Using programming tools like R or Python, the course emphasizes robust model evaluation, selection, and practical applications in forecasting volatility. This rigorous approach prepares students for advanced research and industry roles where sophisticated financial econometric methods are essential for informed decision-making in asset pricing and risk management.

1-Introduction to financial time series 1.1 Examples of financial time series 1.2 Stylized facts 1.3 Tools and software for the financial time series analysis 2- Volatility 2.1 Defining and measuring volatility 2.2 Historical Volatility 2.3 VIX Index 2.4 Realized Volatility 3- Modelling volatility 3.1 Symmetric models of volatility 3.2 Asymmetric models of volatility 3.4 Modelling realized variance 3.5 Volatility forecasting 4-Time Series and Machine Learning 4.1 Linear and nonlinear regressions applied to financial times series 4.2 Examples and study case of the realized variance 4.3 Introduction to decision trees for time series 4.4 Random Forests and Boosting 4.5 Neuronal networks for time series 4.6 Forecasting Realized Variance