M9 - State Space Models

Learning Objectives

The learning goals for this module are:

• Discuss state space models in general;
• Discuss Bayesian Framework;
• Learn about local level, linear trend and basic structure models;
• See how models we are familiar with fit under state space framework (linear regression, exponential smoothing);
• Implement state space model in R.

Slides

Here is a link to the slide deck used in class.

Resources

If you want to learn more about local level, linear trend and BSM please refer to chapters 2, 3 and 4 from the book “An Introduction to State Space Time Series Analysis” by Jacques J. F. Commandeur and Siem Jan Koopman. An online copy of the book can be at Duke library. The specific chapters are also available through the links below.

• Ch2: The Local Level Model
  
• Ch3: The Local Linear Trend Model
  
• Ch4: The Local Level with Seasonal Model
  

Recordings

The three videos below will cover state space models and the corresponding function in R you can use to implement them.

• Bayesian Framework
  

• State Space Models
  

• State Space Models in R
  

Deliverables

For this module you will complete Assignment 8 - Forecasting Competition. Please refer to the Assignments tab for due dates.