[R] circular correlation

Don MacQueen macq at llnl.gov
Tue May 4 00:20:59 CEST 2004


I think you're going to have to decide which wind speed values are 
relevant to which seed collection data points. For example, if you 
collected a seed on Tuesday, is Monday's wind speed relevant or not? 
You've given no indication of what the relationships between your 
wind speed values and your seed collection values might be. Whatever 
the relationship is, you have to use your data in a way that makes 
sense for that relationship. And yes, your basic correlation 
calculation requires one-to-one correspondence. If you have 
many-to-one, you'll have to adapt your data in some way, to make it 
one-to-one. How you adapt it depends on information you haven't 
provided (and isn't an R question either). For example, if seeds 
float about for around 2 days, on average, before settling down to 
the ground, maybe 2 day averages of wind seed are relevant. That's 
the kind of thing you'll have to decide.

-Don

At 2:02 PM -0400 5/3/04, Joseph Dauer wrote:
>I have a problem that deals with correlating wind velocity to seed
>collection data.  The problem lies in that I have a wind data set that
>is contains 2000+ data points and weed collection data on the order of a
>couple hundred.  Both data sets were collected for the same time period,
>but there is not a one-to-one wind velocity->seed location match.  My
>understanding of correlation is that you need equal data sets.  Is there
>a way to compare means and standard deviations (or kappa in circular
>stats) that doesn't require equal data sets?  Thank you in advance. Joe
>
>
>
>Example (simplified):
>
>library(CircStats)
>
>wind<-c(2.1, 2.3, 2.6, 2.1, 2.6, 2.4, 1.2, 1.5) # in radians
>
>seed<-c(1.7, 1.3, 1.5, 1.9, 1.8, 2.3)
>
>circ.cor(wind, seed, test=T)
>
>
>
>
>
>
>
>Joseph Dauer
>
>Master's Student
>
>Weed Ecology
>
>412 ASI
>
>Pennsylvania State University
>
>University Park, PA 16802
>
>
>
>email: jtd152 at psu.edu
>
>office phone: (814) 865 - 6679
>
>http://www.agronomy.psu.edu/weedecology
>
>
>
>
>	[[alternative HTML version deleted]]
>
>______________________________________________
>R-help at stat.math.ethz.ch mailing list
>https://www.stat.math.ethz.ch/mailman/listinfo/r-help
>PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html


-- 
--------------------------------------
Don MacQueen
Environmental Protection Department
Lawrence Livermore National Laboratory
Livermore, CA, USA




More information about the R-help mailing list