[R] Interpolate irregular time series

Gavin Simpson gavin.simpson at ucl.ac.uk
Mon Oct 25 12:01:40 CEST 2010


On Fri, 2010-10-22 at 12:50 +0000, Salim Alexander (salimale) wrote:
> Hi all,
> 
> Issue:
> I have two datasets, one is a regular time series (rain gauge) with
> resolution of 10 minutes. The other one is an irregular time series
> (link). Now I want to analyze the correlation between these two
> datasets with linear regression. The regular time series is a
> data.frame and the irregular time series is a zoo object.
> 
> Problem:
> For the irregular time series (link) I want also a 10 minutes
> resolution. Therefore I smoothed the curve and with the function
> 'loess.smooth()' it's possible to evaluate the points of the curve. R
> has a number code for every date (e.g. "2009-05-01 00:02:11" =
> 1241136131). My idea is to use this number code to receive the
> function value of the smoothed curve. So far, unsuccessfully.
> 
> I read a lot of manuals but I couldn't find an answer. If this issue
> is already answered I apologize.
> 
> Thank a lot,
> Alex

Do you really want to interpolate? The interpolated data won't
necessarily have the same properties as the original data.

Why not model with the time points you do have that are at the same time
point in the two data sets? Or is the problem that the irregular data
don't ever match the sample times of the regular series.

G

-- 
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
 Dr. Gavin Simpson             [t] +44 (0)20 7679 0522
 ECRC, UCL Geography,          [f] +44 (0)20 7679 0565
 Pearson Building,             [e] gavin.simpsonATNOSPAMucl.ac.uk
 Gower Street, London          [w] http://www.ucl.ac.uk/~ucfagls/
 UK. WC1E 6BT.                 [w] http://www.freshwaters.org.uk
%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%



More information about the R-help mailing list