[R] How to find a shift between two curves or data sets

[Hans W. Borchers]

Dear Sébastien,

identifying similarity in curves or time series is one of the main tasks 
in the quite recent field of 'Functional Data analysis' (FDA). See the 
2005 book by Silverman from Springer Verlag or the corresponding Web page 
at url{http://www.psych.mcgill.ca/misc/fda/}.

The 'fda' package on CRAN contains functions developed by Silverman and 
Ramsey and described in that book. You may also be interested in the 'dtw' 
package that provides functions for comparing times series under time 
'warping', i.e., distortions along the time axis.

Hans Werner Borchers
ABB Corporate Research



Sébastien Durand wrote:
> 
> Hello,
> 
> I have a issue here!
> 
> I need to find the offset or shift between two data sets.
> 
> Each data set does not start nor end at the same time and dont even have 
> the same sampling interval (which by the way isn't constant in any of 
> the data set).
> 
> It must be known that the data expressed in both the data set are 
> comming from the same sensor so they should be the same!
> 
> What I am looking for is a way to minimize the differences between the 
> two curves by applying an x offset.
> 
> Would any body have a clue how to perform such action, I simply have no 
> idea were to start.
> 
> Thank you very very much.
> 
> S.
> 

-- 
View this message in context: http://www.nabble.com/How-to-find-a-shift-between-two-curves-or-data-sets-tp19561272p19567696.html
Sent from the R help mailing list archive at Nabble.com.