bssAlphaFit {BSS}

Estimating the smoothness parameter of a Brownian semistationary process

Description

bssAlphaFit uses the 'Change of Frequency' method to estimate the smoothness parameter, alpha, of a BSS process. The COF method needs only minimal assumptions on the parametric form of the kernel, therefore the estimate can be used in any kernel.

Usage

bssAlphaFit(Y, p = 2)

Arguments

Y

a vector of observations of a BSS process at any frequency.

p

the power to be used in the change of frequency method. The default value is p = 2.

Value

The function returns a single value - an estimate for the smoothness parameter alpha.

Examples

N <- 10000
n <- 100
T <- 1.0
theta <- 0.5
beta <- 0.125

kappa <- 3
alpha <- -0.2
lambda <- 1.0


vol <- exponentiatedOrnsteinUhlenbeck(N, n, T, theta, beta)
bss_simulation <- gammaKernelBSS(N, n, T, kappa, alpha, lambda, sigma = vol)
y <- bss_simulation$bss

bssAlphaFit(y, p = 2)