Description Usage Arguments Details Value References
Forcing terms consist of the product of a coefficient function that must be estimated
and a known forcing function that does not. When both of these functions in a forcing
term are defined by B-splines, the product involves an inner product of two B-spline
basis systems. When a product of two forcing terms are required, as is usual in the
the use of the Data2LD package, a great improvement in efficiency of computation can be
acheived by an initial computation of the four-way array or tensor resulting by
taking the inner products of all possible quadruples of the B-spline basis functions.
Memoization is the process of storing these tensors in memory so that they do
not need to be re-computed each time the Data2LD.R function is called.
Memoization is taken care of automatically in the code using the R.cache package,
and is activated the first time a new modelList
object is encountered.
Normally the user does not have to worry about the memorization procedure. It is
possible, however, to manually re-activate the memoization.
However, users may also want to construct these four-way tensors
manually for debugging and other purposes, and this function is made available for
this reason.
1 | Atensorfn(modelList)
|
modelList |
A list object containing the specification of a Data2LD model. Each member of this list contains a list object that defines a single linear differential equation. |
Variable specifications can be set by an invocation of function
make.Variable
for each linear differential equation in the system.
Functions Atensorfn
, BAtensorfn
and Btensorfn
will not
normally be required by users since they are invoked automatically with the
function checkModel
, which is required to be invoked before the
analysis of the data.
A list object of length equal to the number of variables in the system.
Each of the members of this list is a two-dimensional list object, and the members
of this list are the four-way tensors set up as vectors for each of the possible pairs
of forcing terms. All levels of the this list structure are designed to be accessed
numerically by a call like myAtensor[[ivar]][[ntermj]][[ntermk]]
.
J. O. Ramsay and G. Hooker (2017) Dynamic Data Analysis. Springer.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.