Time series analysis and forecasting are indispensable tools in various fields, including economics, social sciences, epidemiology, medicine, and the physical sciences. This course delves into methods for analyzing time series data, with a particular emphasis on financial time series.
The course is highly applied, focusing on practical skills and hands-on learning. Students will learn how to characterize (financial time series), identify dependence and volatility patterns, build statistical models, and evaluate forecasts and risk measures. The emphasis is on developing statistical intuition, understanding the assumptions and limitations of different methods, and acquiring practical implementation skills in a programming language (R). Real financial datasets are used throughout to demonstrate how these techniques operate in practice.
After attending the course students should:
-
Understand time series data and its properties
-
Identify and explain common patterns in time series data
-
Understand autocorrelation and dependence, including correlation, Kendall's tau, Spearman's rho, tail dependence, and stationarity
-
Apply transformations, linear time-series models, volatility modeling, and forecasting and model evaluation
-
Asses financial risk, including Value at Risk (VaR), expected shortfall, and stress testing
