Note: A statistical problem in testing invariance of movement using the phase plane model

Invariant positions on a phase plane of joint angular position and velocity have been proposed as a means by which interlimb coordination may be achieved. This note identifies a problem in the testing, using conventional statistics, of hypotheses derived using the phase plane model. A possible solution is proposed based on directional statistics. Conclusions regarding phase angle invariance, which are based on conventional statistics, must be viewed with some caution.