Program

THE CONFERENCE IS FULLY ONLINE ON ZOOM: PLEASE DOWNLOAD THE LATEST RELEASE OF ZOOM TO BE ABLE TO MOVE FLEXIBLY AROUND

Overview


  • 4 keynote sessions (45min presentation + 10 min discussion)

  • 3 topic sessions (Theory - Forecasting - Macro/Finance): 4 presentations of 20min+5min per session

  • 2 poster sessions (13 posters per session): posters will be in breakout rooms, short presentations will be available beforehand.


All times are Continental European Winter Time (CET, GMT+1)


To accommodate an online format, all sessions are shorter than usual, so we kindly ask all presenters to respect the timing precisely. 



-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------


Friday December 11

9:10am Introduction by the Confernce organizers

9:20-10:15 Keynote Session 1 (45min+10min)  

Chair: Roberto Reno

Monica Billio, Universitá di Venezia (Italy): Bayesian Dynamic Tensor Regression

with Roberto Casarin, Matteo Iacopini, Sylvia Kaufmann

Abstract: Tensor-valued data are becoming increasingly available in economics and this calls for suitable econometric tools. We propose a new dynamic linear model for tensor-valued response variables and covariates that encompasses some well-known econometric models as special cases. Our contribution is manifold. First, we define a tensor autoregressive process (ART), study its properties and derive the associated impulse response function. Second, we exploit the PARAFAC low-rank decomposition for providing a parsimonious parametrization and to incorporate sparsity effects. We also contribute to inference methods for tensors by developing a Bayesian framework which allows for including extra-sample information and for introducing shrinking effects. We apply the ART model to time-varying multilayer networks of international trade and capital stock and study the propagation of shocks across countries, over time and between layers.

break (15min)

10:30-11:20 Session 1A (50min​) THEORY

Chair: Anders Kock
  • Milda Norkute, Lund University (SE): The Factor Analytical Approach in Near Unit Root Interactive Effects Panels
  • Robert AdamekMaastricht University (NL): Lasso Inference for High-Dimensional Time Series
break (10min)

11:30-12:20 Session 1B (50min​) MACRO/FIN

Chair: Alessandra Luati
  • Lorenzo Trapani, University of Nottingham (UK): Factor models with downside risk
  • Jonas Krampe, Mannheim University (GE): Impulse Response Analysis for Sparse High-Dimensional Time Series
break (10min)

12:30-2:15pm (1h45min) POSTER SESSION 1 (13 posters in breakout rooms, see below)

break (15min)

2:30pm-3:20pm Session 2A (50min​) THEORY

Chair: Olivier Scaillet
  • Marine Carrasco, University of  Montreal (CA): Theoretical Comparison of the Functional Principal Component Analysis and Functional Partial Least Squares
  • Morten Nielsen, Queen's University (CA): Inference on the dimension of the nonstationary subspace in functional time series
break (10min)

3:30pm-4:20pm Session 2B (50min​) MACRO/FIN

Chair: Sébastien Laurent
  • Christopher DobronyiUniversity of Toronto (CA): Stochastic Revealed Preference A Non-Parametric Approach
  • Peter Hansen, University of North Carolina (US): A Canonical Representation of Block Matrices with Applications to Covariance and Correlation Matrices
break (10min)

4:30pm-5:25pm Keynote Session 2 (45min+10min, not recorded)

Chair: Frank Kleibergen

Francis X. Diebold, University of Pennsylvania (US): On the Aggregation of Probability Assessments: Regularized Mixtures of Predictive Densities 

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------


Saturday December 12

10:20-11:15 Keynote Session 3 (45min+10min)

Gary Koop, University of Strathclyde (UK): Nowcasting in a Pandemic using Non-Parametric Mixed Frequency VARs

with Florian HUBER, Luca ONORANTE, Michael PFARRHOFER and Josef SCHREINER.

This paper develops Bayesian econometric methods for posterior inference in non-parametric mixed frequency VARs using additive regression trees. We argue that regression tree models are ideally suited for macroeconomic nowcasting in the face of extreme observations, for instance those produced by the COVID-19 pandemic of 2020. This is due to their flexibility and ability to model outliers. In an application involving four major euro area countries, we find substantial improvements in nowcasting performance relative to a linear mixed frequency VAR.

break (15min)

11:30-12:20 Session 3A (50min​) Forecasting

Chair: Eric Hillebrand
  • J Antolin-DiazLondon Business School (UK), Advances in Nowcasting Economic Activity: Secular Trends, Large Shocks and New Data
  • Massimiliano Marcellino, Universitá Bocconi (IT), Nowcasting Tail Risks to Economic Activity with Many Indicators

break (10min)

12:30-1:20pm Session 3B (50min​) Forecasting

Chair: Christian Y. Robert
  • Roberto Casarin, Universitá di Venezia (IT), Dynamic Predictive Density Combinations for Large Financial Data Sets
  • Andrew Patton, Duke University (US), Dynamic Factor Copula Models with Estimated Cluster Assignments
break (15min)

1:30pm-3:15pm (1h45min) POSTER SESSION 2 (13 posters in breakout rooms, see below)

break (15min)

3:30pm-4:25pm Keynote Session 4 (45min+10min)

Chair: Christian Francq

Alexey Onatskiy, University of Cambridge (UK): Some recent results on high-dimensional integrated time series.

I plan to present several recent results on large-dimensional integrated time series. These are taken from some of my own work and from recent
works of others.

4:30pm-5:00pm Acknowledgements, Announcements and Concluding Remarks by the Scientific Chair Christian Gourieroux, the (EC)^2 Director Peter Hansen and the Conference organizers

POSTER SESSION 1

  1. Forecasting commodity prices in a data-rich unstable environments
    Anastasia Allayioti  (University of Warwick, UK) and F. Venditti (European Central Bank) 

  2. Factor and factor loading augmented estimators for panel regression
    Jad Beyhum (Touluse School of Economics, FR) and E. Gautier (Touluse School of Economics, FR) 

  3. The role of elementary schools in SARS-CoV-2 transmission
    Otilia Boldea (Tilburg University, NL) and A. Alipoor (Tilburg University, NL) 

  4. Measuring and Hedging Geopolitical Risk
    Susana Campos-Martins (University of Oxford, UK) and R.F. Engle (New York University, US) 

  5. Do jumps matter in realized volatility modeling and forecasting Empirical evidence and a new mode
    Massimiliano Caporin (Universitá di Padova, IT) 

  6. Dimension Reduction for High Dimensional Vector Autoregressive Models
    Gianluca Cubadda (Universitá di Roma "Tor Vergata", IT) and A. Hecq (Maastricht University, NL)

  7. Modeling and forecasting macroeconomic downside risk
    Andrea De Polis (University of Warwick, UK), D. Delle Monache (Bank of Italy, IT) and I. Petrella (University of Warwick, UK)

  8. Another look into the factor model black box factor interpretation and structural instability
    Thomas Despois
    (Paris School of Economics, FR) and C. Doz (Paris School of Economics, FR) 

  9. Beta Adjusted Covariance Estimation
    Kirill Dragun (Vrije Universiteit Brussel, BE), K. Boudt (University of Gent, BE), O. Sauri (Aalborg University, DK) and S. Vanduffel (Vrije Universiteit Brussel, BE)

  10. The Time-Varying Multivariate Autoregressive Index Model
    Barbara Guardabascio (ISTAT, IT), G. Cubadda (Universitá di Roma "Tor Vergata", IT) and S. Grassi (Universitá di Roma "Tor Vergata", IT)

  11. Forecasting financial markets with semantic network analysis in the COVID19 crisis
    Stefano Grassi (Universitá di Roma "Tor Vergata", IT), A. Fronzetti Colladon (Universitá di Perugia, IT), F. Ravazzolo (Universitá di Bolzano, IT) and F. Violante (ENSAE, FR) 

  12. Higher-order Multi-cumulant Factor Analysis
    Guanglin Huang (Vrije Universiteit Brussel, BE), W. Lu (Chengdu University) and K. Boudt (University of Gent) 

  13. Modeling and forecasting serially dependent yield curves 
    Hao Li (University of Amsterdam, NL)

POSTER SESSION 2

  1. The Macroeconomy as a Random Forest
    Philippe Goulet-Coulombe
    (University of Pennsylvania, US)  

  2. Proper scoring rules for evaluating asymetry in density forecasting
    Matteo Iacopini
    (Universitá di Venezia, IT), F. Ravazzolo (Universitá di Bolzano, IT) and L. Rossini (Queen Mary University, UK) 

  3. Inference in Non-stationary High-Dimensional VARs
    Margaritella Luca
    (Maastricht University, NL), A. Hecq (Maastricht University, NL) and S. Smeekes (Maastricht University, NL)

  4. Measuring Systematic Comovement with Approximate Threshold Group-Factor Models
    Daniele Masacci
    (King's College, UK), M. Rubin (EDHEC, FR) and D. Ruzzi (Bank of Italy, IT) 

  5. Robust Non-Gaussian Inference
    Geert Mesters
    (Vrije Universiteit Amsterdam, NL) and A. Lee (Universitat Pompeu Fabra, ES)

  6. Out of Sample Predictability in Predictive Regressions
    Jean-Yves Pitarakis
    (University of Southampton, UK) and J. Gonzalo (Carlos III University, ES) 

  7. Simulation-based multiple testing for many non-nested multivariate models
    Florian Richard
    (Carleton University, CA) and L. Khalaf (Carleton University, CA)

  8. Filtering the intensity of public concern from Social Media count data with jumps
    Carlo Santagiustina
    (Universitá di Venezia, IT) and M. Iacopini (Universitá di Pisa)

  9. Structured Regularization of High-Dimensional Panel Vector Autoregressions
    Stephan Smeekes
    (Maastricht University, NL), L. Lieb (Maastricht University, NL) and M. Staudigl (Maastricht University, NL)

  10. Unifying Strong and Weak Cross-Sectional Dependence in Spatio-Temporal Analysis
    Quint Wiersma
    (Vrije Universiteit Amsterdam, NL) and J. Shaumburg (Vrije Universiteit Amsterdam, NL) 

  11. Strategic judgement, its game-theoretic foundations, its econometric elicitation
    Emilio Zanetti Chini
    (Universitá di Roma "Sapienza", IT) 

  12. The power of text-based indicators in forecasting the Italian economic activity
    Simone Emiliozzi
    (Banca d'Italia, IT), V. Aprigliano (Banca d'Italia, IT), G. Guaitoli (University of Warwick, UK), A. Luciani (Banca d'Italia, IT), J. Marcucci (Banca d'Italia, IT), Libero Monteforte (Banca d'Italia, IT)

  13. Dynamic portfolio selection with sector-specific regularization
    Wangy Linqi
    (Université catholique de Louvain, BE) and C.M. Hafner (Université catholique de Louvain, BE)