In this paper, we consider daily financial data from various sources (stock market indices, foreign exchange rates and bonds) analyze their multiscaling properties by estimating the parameters of a Markov-switching multifractal (MSM) model with Lognormal volatility components. order to see how well estimated models capture temporal dependency empirical data, estimate compare (generalized) Hurst exponents for both simulated MSM models. general, generate "apparent" long memory in good...

Abstract This paper examines volatility linkages and forecasting for stock foreign exchange markets from a novel perspective by utilizing bivariate Markov‐switching multifractal model that accounts possible interactions between markets. Examining daily data major advanced emerging nations, we show generalized autoregressive conditional heteroskedasticity models generally offer superior forecasts short horizons, particularly returns in Multifractal models, on the other hand, significant...

This article examines whether incorporating investors' uncertainty, as captured by the conditional volatility of sentiment, can help forecasting stock markets. In this regard, using Markov-switching multifractal (MSM) model, we find that uncertainty substantially increase accuracy forecasts market according to forecast encompassing test. We further provide evidence MSM outperforms dynamic correlation-generalized autoregressive heteroskedasticity (DCC-GARCH) model.

In this paper, we consider an extension of the recently proposed bivariate Markov-switching multifractal model Calvet, Fisher, and Thompson [2006. “Volatility Comovement: A Multifrequency Approach.” Journal Econometrics 131: 179–215]. particular, allow correlations between volatility components to be non-homogeneous with two different parameters governing at high low frequencies. Specification tests confirm added explanatory value specification. order explore its practical performance, apply...

In robotic control tasks, policies trained by reinforcement learning (RL) in simulation often experience a performance drop when deployed on physical hardware, due to modeling error, measurement and unpredictable perturbations the real world. Robust RL methods account for this issue approximating worst-case value function during training, but they can be sensitive approximation errors its gradient before training is complete. paper, we hypothesize that Lipschitz regularization help condition...

Abstract We study the pricing implication of climate change news index proposed by Engle et al. (2020). Specifically, we find significant risk premium associated with news. The increases for firms in fossil‐fuel and carbon‐intensive industries, while decreasing low‐emission industries. Furthermore, document that impact is more negative “value” “big” portfolios compared to “growth” “small” portfolios, varies headquartered Democratic states versus Republican states.

In the recent years, a new wave of interest spurred involvement complexity in finance which might provide guideline to understand mechanism financial markets, and researchers with different backgrounds have made increasing contributions introducing techniques methodologies. this paper, Markov-switching multifractal models (MSM) are briefly reviewed multi-scaling properties data analyzed by computing scaling exponents means generalized Hurst exponent H(<i>q</i>). particular we considered...