Anatomy of a Sovereign Debt Crisis: Machine Learning, Real-Time Macro Fundamentals, and CDS Spreads

Abstract

We employ a Least Absolute Shrinkage and Selection Operator (LASSO)-based extension of the Fama–MacBeth procedure to characterize the time-varying dependence of sovereign Credit Default Swap (CDS) spreads on macro indicators during the samples 2009–2013 and 2013–2020. While CDS spreads are mainly reflective of fundamentals, this relationship varies substantially over time, leading to price variation that appears unrelated to fundamentals. The estimated LASSO coefficients are used to endogenously identify macro-sensitivity “regimes” of variation, consistently with a multiple-equilibrium view of the sovereign debt markets.