BivarP (version 1.0)

BiCopGen: Random sample generation of variables X and Y marginal distributions for the Archimedean copula

Description

Generates a random sample of variables X and Y of the marginal distribution for the Archimedean copula. X and Y are of the same size and can be censored.

Usage

BiCopGen(x, rodiny = c("weibull", "weibull"), rodina = "gumbel", No, cens = TRUE, bicens = TRUE, digi = 0)

Arguments

x

vector of these parameters: x[1], x[3] shape ("weibull" or "gamma") or mean ("norm") or meanlog ("lognormal") x[2], x[4] scale ("weibull" or "gamma") or sd ("norm") or sdlog ("lognormal") x[5] copula parameter

rodiny

vector of length 2 of names of the marginal distributions. Distributions can be "weibull", "gamma", "norm", "lnorm". "norm" is the name for the Normal distribution. "lnorm" is the name for the Lognormal distribution.

rodina

copula family. Currently supported families are "gumbel", "clayton" and "frank".

No

sample size

cens

cens = TRUE ... censored sample

bicens

if both bicens and cens are TRUE, both X and Y are censored. If cens is TRUE and bicens is FALSE, one of the X or Y can be uncensored

digi

number of decimal places in the output X and Y

Value

A list with the following components:

X, Y

vectors sizes of No and having digi number of decimal places.

dX

vector size of No and consisting of 0 or 1. If X[i] is censored, dX[i] = 0.

dY

Vector size of No and consisting of 0 or 1. If Y[i] is censored, dY[i] = 0.

Details

Random censoring using distribution function having the same specifications as the original uncensored distribution.