dNTS {TempStable} | R Documentation |
The probability density function (PDF) of the normal tempered stable distributions is not available in closed form. Relies on fast Fourier transform (FFT) applied to the characteristic function.
dNTS(
x,
alpha = NULL,
beta = NULL,
delta = NULL,
lambda = NULL,
mu = NULL,
theta = NULL,
dens_method = "FFT",
a = -20,
b = 20,
nf = 2048
)
x |
A numeric vector of quantile. |
alpha |
A real number between 0 and 1. |
beta |
Any real number. |
delta |
A real number > 0. |
lambda |
A real number > 0. |
mu |
A location parameter, any real number. |
theta |
A vector of all other arguments. |
dens_method |
Currently, useless param, as it does nothing and FFT is always used. |
a |
Starting point of FFT, if |
b |
Ending point of FFT, if |
nf |
Pieces the transformation is divided in. Limited to power-of-two size. |
theta
denotes the parameter vector (alpha, beta, delta, lambda,
mu)
. Either provide the parameters individually OR provide theta
.
Currently, the only method is FFT.
As x
is a numeric vector, the return value is also a numeric
vector of densities.
Massing, T. (2023), 'Parametric Estimation of Tempered Stable Laws'
x <- seq(0,15,0.25)
y <- dNTS(x,0.8,1,1,1,1)
plot(x,y)