This function finds the bivariate joint probability or the binary correlation from the corresponding Gaussian correlation `x`

1 |

`x` |
value of expected correlation between the corresponding Gaussian-distributed variables |

`p0_v1, p0_v2` |
probability of no precipitation occurences for the v1 and v2 time series respectively. See |

`correlation` |
logical numeric value. Default is |

probability of no precipitation occurence in both v1 and v2 simultaneously. It is a matrix if `x`

is a matrix.

This function makes use of normal copula. A graphical introduction to this function (with its inverse) makes is present in the following URL references: http://onlinelibrary.wiley.com/doi/10.1002/joc.2305/abstract
and http://www.sciencedirect.com/science/article/pii/S0022169498001863 (See fig. 1 and par. 3.2)
If the argument `p0_v2`

, the two marginal probabily values must be given as a vector through the argument `p0_v1`

: `p0_v1=c(p0_v1,p0_v2)`

.
In case `x`

is a correlation/covariance matrix the marginal probabilities are given as a vector through the argument `p0_v1`

.

Emanuele Cordano

D.S. Wilks (1998), Multisite Generalization of a Daily Stochastic Precipitation Generation Model, Journal of Hydrology, Volume 210, Issues 1-4, September 1998, Pages 178-191, http://www.sciencedirect.com/science/article/pii/S0022169498001863

Muamaraldin Mhanna and Willy Bauwens (2011) A Stochastic Space-Time Model for the Generation of Daily Rainfall in the Gaza Strip, International Journal of Climatology, Volume 32, Issue 7, pages 1098-1112, http://dx.doi.org/10.1002/joc.2305

1 2 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.