Provides the normalized cumulative sums of squares from a sequence of
coefficients with the diagonal line removed.
Usage
rotcumvar(x)
Arguments
x
vector of coefficients to be cumulatively summed (missing
values excluded)
Value
Vector of coefficients that are the sumulative sum of squared
input coefficients.
Details
The rotated cumulative variance, when plotted, provides a qualitative
way to study the time dependence of the variance of a series. If the
variance is stationary over time, then only small deviations from zero
should be present. If on the other hand the variance is
non-stationary, then large departures may exist. Formal hypothesis
testing may be performed based on boundary crossings of Brownian
bridge processes.
References
Gencay, R., F. Selcuk and B. Whitcher (2001)
An Introduction to Wavelets and Other Filtering Methods in
Finance and Economics,
Academic Press.
Percival, D. B. and A. T. Walden (2000)
Wavelet Methods for Time Series Analysis,
Cambridge University Press.