Bayesian Dynamic Modelling for Multivariate Time Series Analysis

Pr. Mike West

(Duke University)

will give a course on

Bayesian Dynamic Modelling for Multivariate Time Series Analysis

Abstract

This short-course covers principles and methodology of Bayesian dynamic modelling, with a main focus on methodology for multivariate time series analysis and forecasting. Following introductory conceptual and perspective development in univariate settings, the course works through a series of contexts of multivariate dynamic modelling for multiple time series. Key model developments and examples involve analysis, inference and forecasting in financial and econometric contexts, including Bayesian decision analysis overlaying modelling and computational methodology. Several examples are drawn from these areas, while others exemplify use of this range of models in other fields. The course includes recent modelling and methodological developments in multivariate time series and forecasting, and contacts current research frontiers.

Topics

1. Brief Overview of Bayesian Dynamic Modelling and Forecasting
2. Multivariate Time Series: Common Components, Multivariate Volatility
3. Dynamic Latent Factor Models
4. Dynamic Graphical Models
5. Simultaneous Dynamic Graphical Models
6. Dynamic sparsity via latent thresholding– in economic and financial forecasting and decisions

More info on the content here.
 

Programme

Day 1: Monday May 29, 2017 :
10:00 - 10:30      Welcome coffee : Cafeteria of CORE (Lounge, level +1)
10:30 - 12:15      Course
12:15 - 13:30      Welcome Lunch
13:30 - 14:30      Course
14:30 - 15:00      Coffee break
15:00 - 16:00      Course

Day 2-3-4: Tuesday May 30 - Wednesday May 31 - Thursday June 1 :
08:30 - 10:30      Course
10:30 - 11:00      Coffee break
11:00 - 12:45      Course
12:45 - 13:30      Lunch

Courses will take place at the seminar room b-135 (at entrance 34 voie du Roman Pays : level -1)
Welcome/coffee/Lunch will take place in Cafeteria of the CORE institute, Lounge, level +1
 

Location

UCL CORE
34, voie du Roman Pays
B - 1348 Louvain-la-Neuve
Phone : +32 (0)10 47 43 21
 

Registration

Registration is mandatory by May 1^st 2017

• Members of the organizing institutions : free
• Academics & PhD students : 200 Euro
• Other : 500 Euro
• Please transfer the money to: Banque Belfius - 44, Boulevard Pachéco - B 1000 Bruxelles,
  Account number: 091-0015728-43,
  Account holder: UCLouvain, IBAN : BE66.0910.0157.2843, BIC (SWIFT) : GKCCBEBB. With communication: 41.11000.031 + "Mike West"

Registration includes access to course, course material, coffee breaks and a welcome lunch