Fit von Mises distribution to circular data
circvm varlist [if exp] [in range]
circvm varname [if exp] [in range] [, by(byvar)]
Description
circvm fits von Mises (a.k.a. circular normal) distributions to circular variables in varlist with scales between 0 and 360 degrees. With a single varname and a by() option, distributions are fitted separately for groups defined by the distinct values of byvar.
The parameters fitted are the vector mean and the concentration parameter kappa, calculated from the vector strength R by
2 * R + R^3 + 5 * R^5 / 6, R < 0.53; -0.4 + 1.39 * R + 0.43 / (1 - R), R < 0.85; 1 / (R^3 - 4 * R^2 + 3 * R), R >= 0.85.
See Fisher (1993) for details and discussion.
Options
by() indicating grouping is allowed with a single varname.
Examples
. circvm wallasp axisasp . circvm wallasp, by(grade)
References
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 circqvm, circpvm