|
Wine
|
For the purpose of testing the efficiency of DDK methods we choose the classical functional wine spectra dataset. The wine dataset is provided by
Professor Marc Meurens of the University Catholique de Louvain. |
|
add_knots()
|
Add Quasi-optimal Knots for the Piecewise Constant Basis |
|
add_split()
|
adding an optimal splitting point by choosing it from a set of potential splits. |
|
amse()
|
Function average Mean Square Error 'AMSE'
For a given data f, the function 'AMSE' returns the
average mean square error for the data over all samples |
|
mse()
|
--- AuxFun for adding knots ---#
------------------------#
Function mean squared error 'mse'
For a given vector x, the function 'mse' returns the the mean squared error,
mse measures the average of the squares of the errors |
|
opt_split()
|
Finding the optimal splitting point which minimize the average mean square error over the range of the data. |
|
rbetafda()
|
Function to produce generic functional data |
|
split()
|
Evaluating the average mean square errors on the left and right intevals of a given split i |