The Inverse Chi distribution

Density and random generation for the normal-gamma distribution with parameters b, c, g and h. Also contours and confidence regions.

1 2 3 4 5 | ```
dnormgamma(mu, tau, b, c, g, h)
rnormgamma(n, b, c, g, h)
NGacontour(mu, tau, b, c, g, h, p = NULL, ...)
``` |

`mu` |
vector of quantities |

`tau` |
vector of quantities |

`b` |
mean |

`c` |
must be strictly positive. |

`g` |
must be strictly positive. |

`h` |
must be strictly positive. |

`n` |
sample size |

`p` |
probability |

`...` |
Arguments to be passed to the plot function when plotting contours |

If (mu,tau)^T~NGa(b,c,g,h) then mu|tau~N(b,1/(c*tau)) and tau~Ga(g,h). Also mu~t_(2g)(b,h/(gc)).

1 2 3 4 5 6 | ```
dnormgamma(1, 2, 1, 2, 5, 3)
rnormgamma(1, 1, 2, 5, 3)
mu=seq(2,4,len=1000)
tau=seq(0,30,len=1000)
NGacontour(mu,tau,3,1,4,0.35,0.95)
NGacontour(mu,tau,2.5,30,20,2,0.95,add=TRUE,lty=3)
``` |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.