ghypParam: Parameter Sets for the Generalized Hyperbolic Distribution
In sjp/GeneralizedHyperbolic: The generalized hyperbolic distribution

Description Usage Format Author(s) Examples

These objects store different parameter sets of the Generalized Hyperbolic distribution for testing or demonstrating purpose as matrices. Specifically, the parameter sets ghypSmallShape and ghypLargeShape have a constant location parameter of mu = 0. The shape parameter lambda will vary from (-1, -0.5, 0, 1, 1.5) in ghypSmallShape and (-2, -1.5, -1, -0.5, 0, 0.5, 1, 1.5, 2) in ghypLargeShape. The parameter alpha varies from (0, 0.5, 1) in ghypSmallShape and (0, 0.5, 1, 1.5, 2) in ghypLargeShape. In ghypSmallShape the set of values for the beta parameter are (0, 0.5, 1), while in ghypLargeShape they are (0, 0.5, 1, 1.5, 2). The delta parameter will vary from (0, 0.5, 1) in ghypSmallShape and (0, 0.5, 1, 1.5, 2) in ghypLargeShape.

The parameter sets ghypSmallParam and ghypLargeParam have varied values of all 5 parameters. The only difference between these datasets and those of ghypSmallShape and ghypLargeShape are that these also vary the mu parameter. In ghypSmallParam this variation is between (-2, 0, 2) as is also the case in ghypLargeParam.

Note that not all parameter variations may be apparent due to the validity of their combinations.

  ghypSmallShape
  ghypLargeShape
  ghypSmallParam
  ghypLargeParam

ghypSmallShape: a 24 by 5 matrix; ghypLargeShape: a 200 by 5 matrix; ghypSmallParam: a 72 by 5 matrix; ghypLargeParam: a 600 by 5 matrix.

Simon Potter spot023@aucklanduni.ac.nz

data(ghypParam)
## Testing the accuracy of ghypMean
for (i in 1:nrow(ghypSmallParam)) {
  param <- ghypSmallParam[i, ]
  x <- rghyp(1000, param = param)
  sampleMean <- mean(x)
  funMean <- ghypMean(param = param)
  difference <- abs(sampleMean - funMean)
  print(difference)
}