[R] Stationarity of a Time Series

[stephen sefick]

This is a little far afield but I will be back with R/analysis
questions as things progress:

I am working with a dissolve oxygen signal, so there is defiantly
seasonality,  There are local changes in mean and variability (with a
graphical investigation on the order of around seven days).  I am
working in a river and we are monitoring over two hundred miles.  I am
trying to get a hold on the cycles that make up the dissolved oxygen
signal, and then link those things back to the biology (photosynthesis
and respiration), chemistry (chemical oxygen demand), and the physics
(advection (transport of oxygen to the next downstream station) etc.)
We are measuring a suit of chemical, biological, and physical
parameters.  Can the spectral density be valid if there is departure
from stationarity?  if not can I then break the signal up into its
seasonal components and then run spec.pgram on those parts?
Admittedly, I have never delved into signal processing before, so I am
learning, and I work at a nonprofit without access to a university
full of wonderful statisticians- so you guys are it.  Sometimes you
have to jump head first into something to learn.  I'll keep asking
questions and by the grace of inquisitiveness and a little help from
my friends I can figure this out.
thanks to everyone who has helped and anyone who will help in the future.

Stephen Sefick

On Jan 23, 2008 5:48 AM, David Jones <daj at ceh.ac.uk> wrote:
> Prof Brian Ripley wrote:
> > On Tue, 22 Jan 2008, Pfaff, Bernhard Dr. wrote:
> >
> >> Hello Stephen,
> >>
> >> stationarity tests as well as unit root tests have been implemented
> >> in a couple of packages. For instance, as already mentioned:
> >> tseries, but
> >> also uroot, fUnitRoots and urca. See the annotated task view
> >> "Econemtrics" and "Finance" for further information.
> >
> > But note that these tests apply to just a few ways in which a series
> > might be non-stationary: they all seem an econmetrician's view of
> > possible non-stationarity.
> >
> > In the end stationarity is a modelling assumption: it depends on what
> > might have happened but did not.  E.g. a sine wave process is
> > stationary if and only if it has a random (uniform) phase, and you
> > cannot tell that from a single realization.
> >
> > 'Anna Karenina applies'[*] (as to most pure significance tests).
> >
> > [*] Google it if you need elucidation.
> >
>
> Apart from the "drift" type of nonstationarity, other types would be ..
> (i) seasonality;
> (ii) local changes in mean-level;
> (iii) local changes in correlation;
> (iv) local changes in variability.
> Some of these might be made formally stationary as above.
>
> David Jones
>
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>



-- 
Let's not spend our time and resources thinking about things that are
so little or so large that all they really do for us is puff us up and
make us feel like gods.  We are mammals, and have not exhausted the
annoying little problems of being mammals.

								-K. Mullis