getBiCop: Get bivariate random variables
In raphael210/QUtility:

Description Usage Arguments Details Value Note Examples

Compute a bivariate sample distribution drawn from a population with a given . It either computes two random variables, or it takes one existing variable (passed as parameter x) and creates a second variable with the desired correlation.

1	getBiCop(n, rho, mar.fun = rnorm, x = NULL, drop.x = FALSE, ...)

`n`	a integer. number of observations
`rho`	a numeric. the desired correlation
`mar.fun`	the marginal distribution function
`x`	a vector. the existing variable.
`drop.x`	logical. If true, then return a vector of the generated variable.
`...`	other arguments to mar.fun

Get from a forum post: http://stats.stackexchange.com/questions/15011/generate-a-random-variable-with-a-defined-correlation-to-an-existing-variable/15035#15035

a data frame of two variables which correlate with a population correlation of rho, or a vector when drop.x is true.

this is only an approximate solution, i.e., the empirical correlation is not exactly equal to rho.

# -- generate two random variables
df <- getBiCop(100,0.2)
cor(df)
# -- generate another variable with desired correlation on a existing variable
x <- rnorm(100)
df2 <- getBiCop(100,0.2,x=x)
cor(df2)