Modeling and Forecasting Economic and Financial Time Series with State Space models, October 17-18, 2008

Workshop, Sveriges Riksbank

 

Aim

State space models are a powerful tool to tackle difficult inference and forecasting problems common in economic and financial series. Given the emphasis placed on forecasting and nowcasting in modern central banks and other financial institutions, state space models seem a much under-utilized tool in the econometric community. This workshop welcomes theoretical as well as applied contributions. Topics of interest include inference, parameter variation, common factor models, measurement errors and filtering, data revision, and mismatched frequencies.

 

 

Program

  

Thursday, October 16
19:00 

Reception and buffet at the Riksbank                                  

Friday, October 17 
08:45 

 Coffee                                                                           

 

09.00  

Session I. Chair: Paolo Giordani

Forecasting with a model of data revision [paper] [presentation]

Jana Eklund, Bank of England, George Kapetanios, and Simon Price

Discussant: Peter Zadrozny, U.S. Bureau of Labor Statistics [discussion]

Likelihood-based analysis for dynamic factor models [paper] [presentation]

Siem Jan Koopman, Vrije Universiteit Amsterdam

Discussant: Herman van Dijk, Erasmus University [discussion]

Sequential learning, predictive regressions, and optimal
portfolio returns
[paper] [presentation]

Nicholas Polson, University of Chicago                                     

Discussant: Junye Li, Bocconi University [discussion]

13.30

Session II. Chair: Mattias Villani  

Stochastic Model Specification Search [paper] [presentation]

Sylvia Fruehwirth-Schnatter, Johannes Kepler Universität Linz

Discussant: Gabriele Fiorentini, University of Florence [discussion]


Real-time inflation forecasting in a changing world [paper] [presentation]

Jan Groen, Richard Paap and Francesco Ravazzolo, Norges Bank

Discussant: Simon Potter, Federal Reserve Bank of New York

Forecasting macroeconomic time series with locally adaptive signal extraction [paper] [presentation]

Paolo Giordani, Sveriges Riksbank and Mattias Villani
Floor discussion only.

 

 

Saturday, October 18 
08:45

 Coffee                                                                  

 

09.00  

Session III. Chair: TBA

Estimation of time-varying high-dimensional covariance matrices [slides]

Anastasios Plataniotis, and Petros Dellaportas, Athens University

Discussant: Gianni Amisano, European Central Bank [discussion]

Real-time measurement of  business conditions [paper] [presentation]

Boragan Aruoba, Francis X. Diebold, University of Pennsylvania and Chiara Scotti

Discussant: Marta Banbura, European Central Bank [discussion]

Modeling Stochastic Volatility with Leverage and Jumps: A
'Smooth' Particle Filtering Approach
[paper] [presentation]

Michael Pitt, University of Warwick

Discussant: Paolo Giordani, Sveriges Riksbank [discussion]

 

13.30  

Session IV. Chair: Tor Jacobson

Non-linear DSGE models, the central difference Kalman filter, and the mean shifted particle filter [paper] [presentation]
Martin M. Andreasen, University of Aarhus
Floor discussion only


Modeling the Phillips curve with unobserved components [paper] [presentation]
Andrew Harvey, University of Cambridge
Discussant: Drew Creal, Vrije Universiteit Amsterdam [discussion]

 

 

 

 

Format

Papers will be presented in plenary presentations of 30 minutes, followed by 15 minutes of comments by a reviewer and an additional 15 minute plenary discussion.

Expenses

Sveriges Riksbank will refund economy-class travel expenses and cover accommodation at the Hotel Sergel Plaza, in the near vicinity of the Riksbank, for paper presenters and discussants.

 

Paper submission

Deadline for paper submissons was on May 23, 2008.

Organization

The organizing committee consists of Tor Jacobson, Paolo Giordani and Mattias Villani.
Questions can be directed to Secretary Lena Löfgren at lena.lofgren@riksbank.se.

Last reviewed

Content expert

Contact content expert

Fill in the information

To minimize automated spam, please answer the question in the box below.

7 + 7 ?