Workshop on Dynamic Models driven by the Score of Predictive Likelihoods

La Laguna, Tenerife, 9-11th January 2014

uni We organized a small workshop at La Laguna, Tenerife. The focus was on the new class of nonlinear models based on the conditional score. These are known as Dynamic Conditional Score (DCS) or Generalized Autoregressive Score (GAS) models. This workshop was made possible thanks to the contributions of the Dutch National Science Foundation (NWO), the Keynes Fund (University of Cambridge), VU University Amsterdam, and the University of La Laguna (Tenerife). Information on a workshop of 17-18 January 2013, also about dynamic models driven by the score of predictive likelihoods, can be found here. This link also leads to papers and presentations of the 2013 workshop.

Invited speakers:
Peter R. Hansen, European University Institute,
Anders Rahbek, University of Copenhagen,
Andrew Harvey, University of Cambridge,
Siem Jan Koopman, VU University Amsterdam,
Andre Lucas, VU University Amsterdam.

Organizers:
Andrew Harvey (ach34@cam.ac.uk)
Siem Jan Koopman (s.j.koopman@vu.nl)
Andre Lucas (a.lucas@vu.nl)

Program:
Thursday 9 January 2014

    08:45 Welcome
  1. 09:15 Highlights of the score, Andrew Harvey.
  2. 10:00 Optimality of GAS models, Francisco Blasques.
  3. 10:30 Comparing parameter and observation driven models, Charles Bos.
    4. 11:00 coffee/tea
  4. 11:30 Markov Switching GAS models, Marco Bazzi.
  5. 12:00 Score driven correlation models, Erkki Silde.
  6. 12:30 Testing for changing correlation, Stephen Thiele.
    7. 13:00 Lunch
  7. 14:30 Realized factor GARCH, Peter Hansen.
  8. 15:30 Score driven methods of moments estimation, Marcin Zamojski.
    9. 16:00 coffee/tea
  9. 16:30 Time varying Dirichlet processes for liquidity shares, Francesco Calvori.
  10. 17:00 An autoregressive heavy-tailed time varying parameter model with an application to the US inflation, Davide Delle Monache.
  11. 17:30 A model for hydro inflow and wind power capacity for the Brazilian power sector, Cristiano Fernandes.

    12. Friday 10 January 2014

  12. 09:15 Asymptotic properties of the MLE for GAS processes, Andre Lucas.
  13. 10:00 Asymptotic Inference for Beta-t-GARCH, Ryoko Ito.
  14. 10:30 Factor GARCH and common-factor GAS models, Peter Boswijk.
    15. 11:00 coffee/tea
  15. 11:30 GAS models for multivariate dynamic counts, Rutger Lit.
  16. 12:00 CUSUM test for cointegration, Julio Afonso-Rodríguez.
  17. 12:30 Time varying error correction in FX markets, Kazim Azam.
    18. 13:00 Lunch
  18. 14:30 Bootstrapping volatility models, Anders Rahbek.
  19. 15:30 DCS and ARCH-M, Rutger-Jan Lange.
    20. 16:00 coffee/tea
  20. 16:30 Modeling and forecasting the volatility of energy forward returns, Asger Lunde.
  21. 17:00 Robust Asymmetric Stochastic Volatility Models, Xiuping Mao.
  22. 17:30 Volatility During the Financial Crisis Through the Lens of High Frequency Data: A Realized GARCH Approach, Georgiana Banulescu.

    23. Saturday 11 January 2014

  23. 09:00 Spatial GAS models for systemic risk measurement, Julia Schaumburg.
  24. 09:30 A Score driven approach for Gaussian State-Space models with Time-Varying Parameters, Ivan Petrella.
  25. 10:00 Combining State-Space and GAS dynamics, Siem Jan Koopman.
    26. 10:45 General discussion and coffee.