This function samples \(GIG(\lambda, \psi, \chi)\) random variates.
Usage
sim_gig(num_sim, lambda, psi, chi)
Arguments
- num_sim
Number to generate
- lambda
Index of modified Bessel function of third kind.
- psi
Second parameter of GIG. Should be positive.
- chi
Third parameter of GIG. Should be positive.
Details
The density of \(GIG(\lambda, \psi, \chi)\) considered here is as follows.
$$f(x) = \frac{(\psi / \chi)^(\lambda / 2)}{2 K_{\lambda}(\sqrt{\psi \chi})} x^{\lambda - 1} \exp(-\frac{1}{2} (\frac{\chi}{x} + \psi x))$$
where \(x > 0\).
References
Hörmann, W., Leydold, J. Generating generalized inverse Gaussian random variates. Stat Comput 24, 547-557 (2014).
Leydold, J, Hörmann, W.. GIGrvg: Random Variate Generator for the GIG Distribution. R package version 0.8 (2023).
