Estimating and Testing Long-Run Risk Models: International Evidence
Andras Fulop, Junye Li, Hening Liu, Cheng Yan
Management Science · 2025 · Volume 71 · Issue 4
Abstract
We estimate and test long-run risk models using international macroeconomic and financial data. The benchmark model features a representative agent who has recursive preferences with a time preference shock, a persistent component in expected consumption growth, and stochastic volatility in fundamentals characterized by an autoregressive gamma process. We construct a comprehensive data set with quarterly frequency for 10 developed countries and employ an efficient likelihood-based Bayesian method that exploits up-to-date sequential Monte Carlo methods to make full econometric inference. Our empirical findings provide international evidence in support of long-run risks, time-varying preference shocks, and countercyclicality of the stochastic discount factor. We show the existence of a global long-run consumption factor driving equity returns across individual countries. This paper was accepted by Lukas Schmid, finance. Funding: A. Fulop acknowledges support from CY Initiative of Excellence [Grant “Investissements d’Avenir” ANR-16-IDEX-0008], and H. Liu acknowledges support from National Science Foundation of China [Grant 72141305]. Supplemental Material: The internet appendix and data files are available at https://doi.org/10.1287/mnsc.2022.04054 .
Keywords
consumption, equity premium, long-run risk, stochastic discount factor, projection methods, sequential Monte Carlo sampler
Enable JavaScript for citation tools and additional paper interactions.