Skip to content

Spectral analysis

3 messages · David LEDU, (Ted Harding), Gavin Simpson

#
On 06-Jun-07 20:55:09, David LEDU wrote:
There are a lot of possible ramifications to your query,
but for a basic spectral analysis of a series you can use
the function spectrum() in the "stats" package.

What is the role of the "other variable"?

Best wishes,
Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <ted.harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 06-Jun-07                                       Time: 22:34:07
------------------------------ XFMail ------------------------------
#
On Wed, 2007-06-06 at 13:55 -0700, David LEDU wrote:
Invariably data of this nature are irregularly sampled in time, so you
should check whether the in-built spectrum() function is suitable for
your core data. I'm not aware of much else available in R, but one thing
I am aware of is a paper and R code by Mathias et al in the Journal of
Statistical Software:

http://www.jstatsoft.org/index.php?vol=11

It is issue 2 in that volume. This might be more suitable given your
data. The code is a few years old now and there isn't a ready built
package on CRAN so you'll have to compile it yourself.

HTH

G