iossa.result: Summary of Iterative O-SSA results

Description

Various routines to print Iterative Oblique SSA results

Usage

# S3 method for iossa.result
print(x, digits = max(3, getOption("digits") - 3), …)
  # S3 method for iossa.result
summary(object, digits = max(3, getOption("digits") - 3), …)

Arguments

x, object

object of class `iossa.result' or `ossa'

digits

integer, used for number formatting

…

further arguments passed to method

Details

An object of class `iossa.result' is a list with the following fields:

converged: logical, whether algorithm has been converged
iter: the number of OSSA iterations
cond: numeric vector with two elements, condition numbers of the final column and row inner products
initial.tau: numeric vector, proportions of high rank components contribution for each of initial series (denotes how well the series is approximated by a series of finite rank)
tau: numeric vector, proportions of high rank components contribution for each of final series
initial.wcor: W-correlation matrix of the initial nested decomposition
wcor: W-correlations matrix of the final nested decomposition
owcor: oblique W-correlation matrix (see owcor) of the final nested decomposition
initial.rec: list of initial series (reconstructed initial nested decomposition)
kappa, maxiter, tol: Iterative O-SSA procedure parameters

References

Golyandina N. and Shlemov A. (2015): Variations of Singular Spectrum Analysis for separability improvement: non-orthogonal decompositions of time series, Statistics and Its Interface. Vol.8, No 3, P.277-294. http://arxiv.org/abs/1308.4022

Examples

Run this code

# NOT RUN {
# Separate three non-separable sines with different amplitudes
N <- 150
L <- 70

omega1 <- 0.05
omega2 <- 0.06
omega3 <- 0.07

F <- 4*sin(2*pi*omega1 * (1:N)) + 2*sin(2*pi*omega2 * (1:N)) + sin(2*pi*omega3 * (1:N))
s <- ssa(F, L)
ios <- iossa(s, nested.groups = list(1:2, 3:4, 5:6), kappa = NULL, maxiter = 100, tol = 1e-3)

print(ios)
print(ios$iossa.result)
# }

Run the code above in your browser using DataLab

Last chance! 50% off unlimited learning