WOLFRAM NOTEBOOK

WOLFRAM|DEMONSTRATIONS PROJECT

Fractional Ornstein-Uhlenbeck Process

mean reversion
1
mean
FE`Bvalue$$4386332263121317587034223683332728782709
volatility
FE`Cvalue$$4386332263121317587034223683332728782709
initial value
0
Hurst index
FE`Hvalue$$4386332263121317587034223683332728782709
The first two moments (mean and variance) of an OrnsteinUhlenbeck (OU) process are approximated with stochastic expansions (linear combinations of iterated integrals of the paths). The first three parameters are the usual parameters for an OU process: a high mean reversion makes the convergence to the mean faster and a high volatility increases the variance. The Hurst index controls the roughness of the fractional Brownian motion: the higher the value, the smoother the path. At Hurst index 0.5, this reduces to the usual Brownian motion.
This is a simple application of the theory of rough paths. The same approach can be used for a large class of drivers, not just fractional Brownian motion, and is applicable to more complicated models. Once a stochastic expansion is derived, it can be used for local simulation, moment approximations, or parameter estimation.
Wolfram Cloud

You are using a browser not supported by the Wolfram Cloud

Supported browsers include recent versions of Chrome, Edge, Firefox and Safari.


I understand and wish to continue anyway »

You are using a browser not supported by the Wolfram Cloud. Supported browsers include recent versions of Chrome, Edge, Firefox and Safari.