wDsensitivity
builds a sensitivity function for the weighted D-, D_s or D_A-optimality criterion which relies on defaults to speed up evaluation.
Wynn
for instance requires this behaviour/protocol.
wDsensitivity(A = NULL, parNames = NULL, defaults = list(x = NULL,
desw = NULL, desx = NULL, mods = NULL, modw = NULL))
for
D-optimality: NULL
D_s-optimality: a vector of names or indices, the subset of parameters of interest.
D_A-optimality: either
directly: a matrix without row names.
indirectly: a matrix with row names corresponding to the parameters.
a vector of names or indices, the subset of parameters to use. Defaults to the parameters for which the Fisher information is available.
a named list of default values.
The value NULL
is equivalent to absence.
wDsensitivity
returns function(x=NULL, desw=NULL, desx=NULL, mods=NULL, modw=NULL)
, the sensitivity function.
It's attributes contain this function's arguments.
Indices and rows of an unnamed matrix supplied to argument A
correspond to the subset of parameters defined by argument parNames
.
For efficiency reasons the returned function won't complain about missing arguments immediately, leading to strange errors. Please ensure that all arguments are specified at all times. This behaviour might change in future releases.