Time Series

This introductory course on time series—that is, a sequence of observations made over time—provides an essential toolkit for analyzing this type of data, which is frequently encountered in a wide range of applications: pollutant concentrations in the air over time, blood glucose levels over time, product sales at a supermarket, stock prices on the stock market, etc. This course focuses both on the mathematical presentation of concepts and on the more technical aspects of implementing these methods. Numerical examples are provided using the R software.

Master the key concepts of time series modeling. Be able to propose an appropriate method for modeling and forecasting a time series.

Analysis, Probability, and Statistics (L3 level).




Recommended prerequisites: first semester of the M1 SSD program

 CCI + Project

• Descriptive Analysis of a Time Series
• ARMA processes, autocorrelation functions, and partial autocorrelation functions.
• Spectral Analysis
• Linear forecasting: Yule-Walker equations, Durbin-Watson algorithm
• Estimate 
• Testing the Briefcase

Hours:
Lectures: 15 hours
Tutorials: 15 hours
Lab sessions:
Fieldwork: