R help - Apr 2008 - Cross Spectrum Analysis

I am reading some documentation about Cross Spectrum Analysis as a technique
to compare spectra.
My understanding is  that it estimates the correlation strength between
quasi-periodic structures embedded in two signals. I believe it may be
useful for my signals  analysis.

I was referred to the R  functions that  implement this type of analysis. I
tried all the examples which generated a series of fancy plots. But  I need
to work on the numerical results.

I have read that the following info is available through Cross Spectra
analysis:
*Cross-periodogram, Cross-Density, Quadrature-density, Cross-amplitude, Squared
Coherency, Gain, and Phase Shift*
I went through a couple of the two-series (bivariate) cross-spectrum
analysis examples with R.
I also printed out the attributes of the analysis (see the following). I
cannot quite match the above quantities with the attributes/features output
of cross-spectra analysis with R.
I would greatly appreciate some explanation (which is what) and seeing some
more worked out examples.
> attributes(mfdeaths.spc)
$names
 [1] "freq"      "spec"      "coh"      
"phase"     "kernel"    "df"
 [7] "bandwidth" "n.used"    "orig.n"   
"series"    "snames"    "method"
[13] "taper"     "pad"       "detrend"  
"demean"

$class
[1] "spec"


Thank you so much.

Yours Faithfully,
-- 
Maura E.M

	[[alternative HTML version deleted]]

$names
 [1] "freq"      "spec"      "coh"      
"phase"     "kernel"    "df"
 [7] "bandwidth" "n.used"    "orig.n"   
"series"    "snames"    "method"
[13] "taper"     "pad"       "detrend"  
"demean"

$freq and $spec are used to plot the power spectrum.  freq is the x-axis and
spec is the y-axis.  $coh is the squared coherency between the two signals
in your case and I believe that this is also plotted against frequency.
This is your "correlation" strength.  Phase I haven't been able to
figure
out- I think that it is some sort of estimator for the phase shift.  to get
either phase or coherency plot add the plot.type argument to your plot
command

x <- spectrum(yourdata, log="no") #this will plot it without a log
scale I
find it useful to look at both the no log plot and then the logscale plot
(just remove the log="no")

plot(x, plot.type="marginal")  #this is the default type (the
powerspectrum)
plot(x, plot.type="phase")
plot(x, plot.type="coherency")

also just look at

?spectrum
schumway is a good book - I think it is something like time series analysis
with examples in R

hope this helps

stephen


On Tue, Apr 29, 2008 at 8:54 PM, Maura E Monville
<maura.monville@gmail.com>
wrote:
> I am reading some documentation about Cross Spectrum Analysis as a
> technique
> to compare spectra.
> My understanding is  that it estimates the correlation strength between
> quasi-periodic structures embedded in two signals. I believe it may be
> useful for my signals  analysis.
>
> I was referred to the R  functions that  implement this type of analysis.
> I
> tried all the examples which generated a series of fancy plots. But  I
> need
> to work on the numerical results.
>
> I have read that the following info is available through Cross Spectra
> analysis:
> *Cross-periodogram, Cross-Density, Quadrature-density, Cross-amplitude,
> Squared
> Coherency, Gain, and Phase Shift*
> I went through a couple of the two-series (bivariate) cross-spectrum
> analysis examples with R.
> I also printed out the attributes of the analysis (see the following). I
> cannot quite match the above quantities with the attributes/features
> output
> of cross-spectra analysis with R.
> I would greatly appreciate some explanation (which is what) and seeing
> some
> more worked out examples.
>
> > attributes(mfdeaths.spc)
> $names
>  [1] "freq"      "spec"      "coh"      
"phase"     "kernel"    "df"
>  [7] "bandwidth" "n.used"    "orig.n"   
"series"    "snames"    "method"
> [13] "taper"     "pad"       "detrend"  
"demean"
>
> $class
> [1] "spec"
>
>
> Thank you so much.
>
> Yours Faithfully,
> --
> Maura E.M
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@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

	[[alternative HTML version deleted]]

Hi

Is anyone know how could I find the cross spectrum?

from the spectrum function, it only give the spectrum for each individual
series.

Thanks
Aftar
-- 
View this message in context:
http://r.789695.n4.nabble.com/Cross-Spectrum-Analysis-tp855188p2473397.html
Sent from the R help mailing list archive at Nabble.com.

On Sep 2, 2010, at 1:00 AM, aftar wrote:
>
> Hi
>
> Is anyone know how could I find the cross spectrum?
>
> from the spectrum function, it only give the spectrum for each  
> individual
> series.
I read the manual very differently. It is telling me that you _do_ get  
cross spectrum results in the "coh" matrix:

"VALUE
coh    NULL for univariate series. For multivariate time series, a  
matrix containing the squared coherency between different series.  
Column i + (j - 1) * (j - 2)/2 of coh contains the squared coherency  
between columns i and j ofx, where i < j."

And there is a link on that help page to a help page that includes the  
plot.spec.coherency function.

This response from Prof Ripley (very easily found on an RSiteSearch  
search for "cross spectrum") has a further link to a supplement to
V&R4:
http://finzi.psych.upenn.edu/Rhelp10/2009-November/219526.html

http://www.stats.ox.ac.uk/pub/MASS4/VR4stat.pdf

... which discusses coherency and illustrates processing of the "coh"
object.
-- 

David Winsemius, MD
West Hartford, CT