var.rv, cov.rv and cor.rv compute the distribution of the variance statistic of x and the distribution of the covariance statistic or the correlation statistic of x and y if these are vectors. If x and y are matrices then the covariances (or correlations) between the columns of x and the columns of y are computed.

cor.rv(x, y = NULL, ...)

cov.rv(x, y = NULL, ...)

sd.rv(x, na.rm = FALSE)

var.rv(x, ...)

Arguments

x

a numeric or random vector, matrix, or a data frame

y

NULL (default) or a vector, matrix or data frame with compatible dimensions to x. The default is equivalent to y = x (but more efficient).

...

arguments passed to stats::var

na.rm

logical. Should missing values be removed?

Value

A random vector or array.

Details

These functions are compatible with both numeric and rv objects. To make your code compatible with rv objects, use e.g. sd.rv instead of sd.

The functions cov.rv is implemented by applying the corresponding numerical function to the rows of the simulation matrices of x and y and forming a new rv object from the resulting vector of simulations. Alternatively x may be a random matrix (and y NULL). %Then the numerical function cov.

cor.rv works similarly, but returns the distribution of the correlation statistic (i.e. function).

var.rv computes the distribution of the variance statistic. sd.rv is the square root of the result obtained by var.rv.

References

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").

Author

Jouni Kerman jouni@kerman.com

Examples


  #