R中的广义双曲分布

Question

如何使用包“广义双曲分布”来使NIG分布中的参数适合数据集？

Answer 1

Developing @Prasad Chalasani's comment, you need to install the ghyp package. When I did, the packages gtools , gdata , numDeriv and gplots were also installed automatically. However, I then got the same error as you Error: could not find function "fit.NIGuv" , which I resolved by installing the bitops package manually.

The documentation gives an example of the following code using fit.NIGuv()

library(ghyp)
data(smi.stocks)
nig.fit <- fit.NIGuv(smi.stocks[,"SMI"], opt.pars = c(alpha.bar = FALSE),
                     alpha.bar = 1, control = list(abs.tol = 1e-8))
nig.fit
summary(nig.fit)
hist(nig.fit)

where the output includes

Asymmetric Normal Inverse Gaussian Distribution:

Parameters:
    alpha.bar            mu         sigma         gamma 
 1.0000000000  0.0008370731  0.0112098776 -0.0007205143 

log-likelihood:
5495.705

and I think this is the kind of thing you are looking for.