Research 

Testing for the Interconnection Channel 

• with Bertrand Candelon - submitted

• LIDAM Discussion Paper LFIN - 2025/05 

• Abstract: When modeling the dynamics of a large cross section of interdependent variables, the employment of small scale Vector Autoregressive (VAR) models augmented by few factors is the typical solution to avoid the proliferation of parameters in large heterogeneous VARs. The factors' are typically extracted as a linear combination of the variables under analysis. Their loadings/weights can be estimated or derived from economic literature, and are usually interpreted as interconnection channels. We propose a novel Likelihood Ratio Test procedure to empirically evaluate the chosen set of weights, and show that testing is fundamental for valid inferences. We exploit the intuition that, if the factors employed are empirically valid, no residual information from the cross section remains statistically significant. The proposed test is intuitive, easy to implement, and presents very good finite sample properties. In the empirical exercise, we test several interconnection channels for the sovereign bond market in the euro area.

• Presentations: 12th International Workshop of Methods in International Finance Network (MIFN), 19th EconomiX-CNRS and Université de Paris Nanterre Econometrics day,  14th Financial Risks International Forum, the 7th RCEA Time Series Workshop, 8th Annual Conference of the International Association for Applied Econometrics (IAAE), 17th Belgian Financial Research Forum, the 27th Annual International Conference on Macroeconomic Analysis and International Finance (ICMAIF),  40th European Economic Association Congress (EEA), 5th Sailing the Macro Workshop.

Modeling Interdependent Assets: A Global Perspective

• with Francesco Roccazzella 

• Abstract: Existing literature acknowledges two key characteristics of asset returns' dynamics: they are interconnected and drifting. We propose modeling these features jointly using a Global Error Correction Model and demonstrate that this novel methodology systematically improves the fit of buy-and-hold strategies across asset classes. We establish the equivalence between Generalized Impulse Response Functions and the conditional sensitivity of asset returns to unexpected global financial market fluctuations—analogous to the \textit{beta} in the CAPM framework. Notably, portfolios with low exposure to systemic market shocks (i.e., low beta) outperform traditional strategies aimed at reducing market risk, such as minimum variance or diversified bond portfolios, particularly over annual holding periods.

• Presentations: 2024 International Conference in Finance, Accounting, and Banking, 41st International Conference of the French Finance Association (AFFI), the 29th Annual International Conference on Macroeconomic Analysis and International Finance (ICMAIF),  2025 Annual Conferences of the International Association for Applied Econometrics (IAAE).

Robust Bond Risk Premia: Sparse Macroeconomic Information Matters

• with Francesco Roccazzella and Jonas Striaukas 

• Abstract: There is no consensus on whether macroeconomic information significantly improves the prediction of bond risk premia. Existing studies have only examined a limited set of macroeconomic factors, despite the inherently high-dimensional nature of macroeconomic information. We instead propose to test the full set of available macroeconomic variables, assessing the significance of the sparse component in high-dimensional factor-augmented predictive regressions. Three key findings emerge. First, sparse macroeconomic information does matter for bond risk premia prediction. Second, significance emerges consistently from labour market outcomes. Third, the inclusion of labour market variables improves both in- and out-of-sample predictions of bonds excess returns.

The Impact of Wildfires on Loss Given Default: Evidence from Defaulted Consumer Credits

Fragmentation in the European Monetary Union: Is it really over?

European Economic Forecast. Spring 2015.