English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One of the standardized features of financial data is that log-returns areuncorrelated, but absolute log-returns or their squares namely the fluctuatingvolatility are correlated and is characterized by heavy tailed in the sensethat some moment of the absolute log-returns is infinite and typicallynon-Gaussian [20]. And this last characteristic change accordantly to differenttimescales. We propose to model this long-memory phenomenon by superstatisticaldynamics and provide a Bayesian Inference methodology drawing onMetropolis-Hasting random walk sampling to determine which superstatisticsamong inverse-Gamma and log-Normal describe the best log-returns complexity ondifferent timescales, from high to low frequency. We show that on smallertimescales (minutes) even though the Inverse-Gamma superstatistics works thebest, the log-Normal model remains very reliable and suitable to fit theabsolute log-returns probability density distribution with strong capacity ofdescribing heavy tails and power law decays. On larger timescales (daily), weshow in terms of Bayes factor that the inverse-Gamma superstatistics ispreferred to the log-Normal model. We also show evidence of a transition ofstatistics from power law decay on small timescales to exponential decay onlarge scale with less heavy tails meaning that on larger time scales thefluctuating volatility tend to be memoryless, consequently superstatisticsbecomes less relevant.

Bayesian inference and superstatistics to describe long memory processes of financial time series