.-
help for ^circcorr^
.-

Correlation for circular data
-----------------------------

    ^circcorr^ varname1 varname2 [^if^ exp] [^in^ range]

Description
-----------

^circcorr^ produces a correlation coefficient appropriate for two
circular variables taking on values between 0 and 360 degrees.

The correlation is defined for n values of two such variables x and y as

               SUM sin(x[i] - x[j]) sin(y[i] - y[j])
               i<j
r_T =   ----------------------------------------------------
                      2                     2
        ROOT [ SUM sin (x[i] - x[j]) SUM sin (y[i] - y[j]) ]
               i<j                   i<j

and takes on values between -1 and 1.

The P-value associated with r_T can be computed for large samples,
say n >= 25, but depends on the distribution of x and y. If either has a
mean resultant length (vector strength) of 0, then n * r_T is double
exponential. Otherwise, ROOT of n * r_T has a Gaussian (normal)
distribution. Both P-values are calculated.

See Fisher (1993, pp.151-153) for details, but note that both U terms in
(6.40) on p.152 should be rooted.


Example
-------

        . ^circcorr wallasp axisasp^


Saved values
------------

     S_1  number of observations
     S_2  correlation
     S_3  Z of Fisher (1993, 6.40, but see above)
     S_4  P-value from Z (vector strengths non-zero)
     S_5  P-value (either vector strength zero)


Reference
---------

Fisher, N.I. 1993. Statistical analysis of circular data. Cambridge:
Cambridge University Press.


Author
------
         Nicholas J. Cox, University of Durham, U.K.
         n.j.cox@@durham.ac.uk

Also see
--------

On-line: help for @circplot@, @circlcco@