The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
Added covercorr(), a unified front-end that
dispatches to the appropriate coverage correlation routine based on its
input. It accepts a pair of variables (x, y),
a list of variables, or a matrix/data frame/data table (each column
treated as a variable), and chooses random or deterministic reference
points via the reference argument.
Added coverage_correlation_grid(), a variant of
coverage_correlation() that accepts user-supplied reference
points (u, v) instead of generating them
randomly. When both inputs are one-dimensional and no points are
supplied, it defaults to the deterministic uniform grid
{1/n, ..., 1}, making the rank transformation
reproducible.
Added coverage_correlation_K(), which generalises
the coefficient from a pair of variables to K mutually
compared variables supplied as a list.
Added coverage_correlation_K_grid(), the
K-variable counterpart of
coverage_correlation_grid(), accepting an optional
grid list of reference points and defaulting to the uniform
grid for one-dimensional inputs.
All coverage correlation functions now return an object of class
"covercorr" with print() and
summary() methods for readable output.
The fixed-grid pairwise p-value now uses the correct null centering for the deterministic-grid case, including the second-order term in the expansion of the null mean.
Explicitly supplied M (Monte Carlo sample size) is
now coerced to an integer and validated, so passing a plain numeric
value no longer triggers a low-level error.
NA handling now preserves matrix structure
throughout (using drop = FALSE), and rows are dropped
consistently across all inputs and reference grids.
K-variable (K > 2) fixed-grid case. In that
case coverage_correlation_K_grid() returns
pval = NA (with pval_available = FALSE) and
emits an informative message; the statistic itself is still computed.
The K = 2 fixed-grid case returns a valid p-value
consistent with coverage_correlation_grid().coverage_correlation() for the
coverage correlation coefficient between two random variables or
vectors, with exact and Monte Carlo computation methods and optional
visualisation.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.