Towards Generic Simulation for Demanding Stochastic Processes

Abstract

We outline and test a new methodology for genuine simulation of stochastic processes with any dependence structure and any marginal distribution. We reproduce time dependence with a generalized, time symmetric or asymmetric, moving-average scheme. This implements linear filtering of non-Gaussian white noise, with the weights of the filter determined by analytical equations, in terms of the autocovariance of the process. We approximate the marginal distribution of the process, irrespective of its type, using a number of its cumulants, which in turn determine the cumulants of white noise, in a manner that can readily support the generation of random numbers from that approximation, so that it be applicable for stochastic simulation. The simulation method is genuine as it uses the process of interest directly, without any transformation (e.g., normalization). We illustrate the method in a number of synthetic and real-world applications, with either persistence or antipersistence, and with non-Gaussian marginal distributions that are bounded, thus making the problem more demanding. These include distributions bounded from both sides, such as uniform, and bounded from below, such as exponential and Pareto, possibly having a discontinuity at the origin (intermittence). All examples studied show the satisfactory performance of the method.

Sci: An Inclusive, Multidisciplinary Scientific Journal

“…The series of the Feature Papers Editors Collection Special Issues continues. In 2021, Sci had ten such manuscripts online and seven under consideration [14][15][16][17][18][19][20][21][22][23]. In the Feature Papers Editors Collection 2021, we are also launching the "What's it about?"…”

Revisiting causality using stochastics: 1. Theory

“…Conversely, in a deterministic system with linear dynamics, any perturbation of initial conditions dies off, as does the potential for change-and hence the importance of nonlinearity in deterministic approaches [33,52,53]. -In stochastics, linearity is not an (over)simplification of the dynamics but has some sound justification, as indicated by the already mentioned Wold decomposition, in which the stochastic component (the regular process) is linearly equivalent to a white noise process (i.e.…”

Estimation of Hydropower Potential Using Bayesian and Stochastic Approaches for Streamflow Simulation and Accounting for the Intermediate Storage Retention

“…Finally, v is a white-noise process that is used to preserve the marginal structure of the process. For example, for fGn, v follows a Gaussian distribution, whereas for non-Gaussian distributions of the parent process, a heavy-tailed distribution can be applied [50,51].…”

“…Here, we use an algorithm that can explicitly preserve an adequate and necessary number of moments from the marginal function of the gamma distribution and the second-order Hurst-Kolmogorov dependence structure, as identified and expressed through the less statistical biased metric of the climacogram, for a vast range of scales ( [49]; for the merits of this method and applications of explicit preservation of four to six marginal moments, see [50]. For the preservation of as many required moments, see [51]).…”