Coefficient functions in linear differential systems are often required to be strictly
positive. This can be achieved by defining the coefficient function to be the
exponential of a functional data object. This function evaluates the partial
derivatives of the coefficient function with respect to the coefficients in the
functional data object. It is used as the member fun.Dfd of a user-defined
coefficient function.
fun.Dexplinear(tvec, bvec, Bbasisobj)A vector of times at which the function is to be evaluated.
A vector or a single column of coefficient values for the functional data object.
A functional basis object.
A matrix with the number of rows equal to the length of argument tvec and
number of columns equal to the number of basis functions.
This matrix contains the partial derivatives with respect to the coefficients
defining the functional data object evaluated at the time values in argument
tvec.
The length of argument bvec must match the number of basis functions in
argument Bbasisobj.
J. O. Ramsay and G. Hooker (2017) Dynamic Data Analysis. Springer.