rvmapply is the rv-compatible version of mapply.  It
repeats the function FUN for each joint draw of the random (or
constant) arguments, while allowing vectorizing.
rvmapply(
  FUN,
  ...,
  MoreArgs = NULL,
  SIMPLIFY = FALSE,
  USE.NAMES = TRUE,
  SAMPLESIZE = NULL
)the function to apply to the simulations of X.
further arguments to FUN, possibly random vectors or
array.
Other args passed to FUN `as is' (must not be rv
objects unless the function already accepts them)
logical; see mapply for details
logical; see mapply for details
if specified, takes a (joint) sample of the simulations and processes only them.
Depends on FUN; a random vector or array if FUN is
numeric.
rvmapply applies a given function to each simulation (vector or
array) of the given random vectors, returning a the results as a random
vector or array.
The dimensions of each joint draw are preserved.  For an example, see
solve, that returns the distribution of the inverse of a
random matrix.
Usually used in functions that implement an 'rv'-compatible routine.
For an example of a function that uses SAMPLESIZE,
abline.
If the function (FUN) has an argument ``FUN", it must be
specified within the list supplied to MoreArgs.
Kerman, J. and Gelman, A. (2007). Manipulating and Summarizing Posterior Simulations Using Random Variable Objects. Statistics and Computing 17:3, 235-244.
See also vignette("rv").