We study the evolution WTI returns using a novel approach proposed by Chang, Choi and Park (2017). That is, instead of modeling the process that governs the switching between volatility regimes as exogenous, switching depends on whether the underlying latent factor exceeds or not a threshold. Moreover, innovations in the latent factor are assumed to be correlated with the innovations in the previous period; hence, future transitions, say from a low to a high volatility regime, depend on past states. We then investigate what macroeconomic variables explain the fluctuations in the mean and volatility factors using two regularization methods (adaptive LASSO and adaptive Elastic-Net). We find that two indicators of aggregate demand and monetary policy play an important role in explaining the variation in the full sample.
© 2021 GitHub, Inc. Terms Privacy Security Status Docs Contact GitHub Pricing API Training Blog About