Time Series 1

A first Time Series course for 2rd year students

General Information

This is an introductory course on time series for all second-year ENSAI students. You will find tutorials, exercises, practical sessions, and some of their solutions in the Git folder: Series Temporelles 1.

All documents in this course are written in French.

Objectives:

  • Know the main linear models used and their characteristics.
  • Be able to estimate the parameters of the models and test their validity.
  • Recognize the main characteristics of a time series using standard graphical tools.
  • Know how to conduct a complete statistical approach: finding suitable models, verifying their validity for the data, and making forecasts of future values.

Content:

Chapter 0: Organization, introduction, and objectives of the course.

Chapter 1: Estimation and elimination of deterministic components by linear filtering: trend and seasonality.

Chapter 2: Stationary processes in discrete time: stationarity, ACF and PACF.

Chapter 3: ARMA processes, causality, invertibility, innovation, estimation.

Chapter 4: SARIMA processes and the Box-Jenkins method.

Chapter 5: Exponential smoothing

Chapter 6: Some generalizations: exogenous contributions, ARMAX processes, and cross-correlation. Heteroscedasticity and (G)ARCH processes.

Organization:

  • Lectures: 18 hours divided into 6 sessions.
  • Tutorials and solutions of exercices: 2 sessions of 3 hours.
  • Practical sessions (with R): 3 sessions of 3 hours.