Description Usage Arguments Details Author(s)
Optimal Smoothing Matrix
1 2 | smoothing.matrix(R, startup_period = 10, training_period = 60,
seed = 9999, trials = 50, method = "L-BFGS-B", lambda = 0.2)
|
R |
data |
startup_period |
length of samples required to calculate initial values |
training_period |
length of samples required to calculate forecast errors for evalualating the objective |
seed |
random seed to replicate the starting values for optimization |
trials |
number of strarting values to try for any optimization. Large number of trials for high dimensions can be time consuming |
method |
optimization method to use to evaluate an estimate of smoothing matrix. Default is L-BFGS-B |
lambda |
known constant as described in the paper. Defaulted to 0.2 |
Calcuation of smoothing matrix is done by assuming that the smoothing matrix is symmetrix and has a spectral decomposition. The orthogonal matrix in the decomposition is calculated using the product of givens rotation matrices and requires d(d-1)/2 angles for a d dimensional matrix. The eigenvalues are restricted to lie in [0,1].
Rohit Arora
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.