Generalized mixtures of Gaussian processes with an application to Bitcoin daily price analysis

Year 2025, Early Access, 1 - 16

Anthony Desmond Heydar Ali Mardani-fard , Ahad Jamalizadeh , Roohollah Roozegar

https://doi.org/10.15672/hujms.1472824

Abstract

In this paper, we apply Rice’s formula, typically employed to calculate the mean number of upcrossings for stationary Gaussian processes, and extend it to the broader framework of generalized mixtures of Gaussian processes. The class of generalized mixtures of Gaussian distributions, recently introduced by [3], is highly comprehensive and includes significant subclasses such as mean mixtures of Gaussian, variance mixtures of Gaussian, meanvariance mixtures of Gaussian, and even scale mixtures of skew-Gaussian distributions. Consequently, our results hold substantial generality, enabling the extension of Rice’s formula to address specific scenarios within these subclasses.

Keywords

Crossings, Generalized mixture of Gaussian distribution, Rice’s formula

References

• [1] K. Aas and I.H. Haff, The generalized hyperbolic skew Student’s t-distribution, J. Financ. Econ. 4, 275-309, 2006. [2] M. Abdi, M. Madadi, N. Balakrishnan and A. Jamalizadeh, Family of mean-mixtures of multivariate normal distributions: Properties, inference and assessment of multivariate skewness, J. Multivar. Anal. 181, 104679, 2021. [3] R.B. Arellano-Valle and A. Azzalini, A formulation for continuous mixtures of multivariate Gaussian distributions, J. Multivar. Anal. 185, 104780, 2021.